{"source":"AIMap","schema":"self-host-models/v1","updated":"2026-10-22","generatedAt":"2026-10-22T12:12:51.036Z","note":"Official open-weight models (Hugging Face official orgs only). params in billions; mem.* in GB = weights × bpw/8 × 1.1 + 0.5 + KV(8K, FP16, 1 request) – estimates. fits = smallest hardware with total ≤ 90% of usable memory. null = not published / not computable.","method":{"bpw":{"bf16":16,"fp8":8.5,"q4":4.85},"overhead":"weights × 10% + 0.5 GB","kvCtx":8192,"kvBytes":2,"fitRatio":0.9,"macUsable":"≤36GB: 2/3, larger: 3/4","spark":0.9},"pages":{"en":"https://aimap.page/en/models/compute/open-models/","zh-hans":"https://aimap.page/zh-hans/models/compute/open-models/"},"families":[{"id":"qwen","zh":"通义千问 Qwen","en":"Qwen","pubZh":"阿里巴巴通义","pubEn":"Alibaba Qwen","origin":"cn","count":112,"variants":345,"latest":"2026-10-09","orgs":["Qwen"]},{"id":"granite","zh":"IBM Granite","en":"IBM Granite","pubZh":"IBM","pubEn":"IBM","origin":"intl","count":67,"variants":147,"latest":"2026-10-14","orgs":["ibm-granite"]},{"id":"nemotron","zh":"NVIDIA Nemotron","en":"NVIDIA Nemotron","pubZh":"英伟达","pubEn":"NVIDIA","origin":"intl","count":62,"variants":108,"latest":"2026-10-16","orgs":["nvidia"]},{"id":"gemma","zh":"Gemma","en":"Gemma","pubZh":"Google","pubEn":"Google","origin":"intl","count":48,"variants":87,"latest":"2026-09-14","orgs":["google"]},{"id":"mistral","zh":"Mistral / Magistral / Devstral","en":"Mistral / Magistral / Devstral","pubZh":"Mistral AI","pubEn":"Mistral AI","origin":"intl","count":35,"variants":61,"latest":"2026-10-08","orgs":["mistralai"]},{"id":"glm","zh":"GLM / CogVideoX（智谱）","en":"GLM / CogVideoX (Z.ai)","pubZh":"智谱 Z.ai","pubEn":"Z.ai (Zhipu)","origin":"cn","count":35,"variants":55,"latest":"2026-08-25","orgs":["zai-org"]},{"id":"deepseek","zh":"DeepSeek","en":"DeepSeek","pubZh":"深度求索","pubEn":"DeepSeek","origin":"cn","count":34,"variants":42,"latest":"2026-10-17","orgs":["deepseek-ai"]},{"id":"olmo","zh":"Ai2 OLMo / Molmo","en":"Ai2 OLMo / Molmo","pubZh":"Allen AI（Ai2）","pubEn":"Allen Institute for AI","origin":"intl","count":31,"variants":52,"latest":"2026-05-04","orgs":["allenai"]},{"id":"ling","zh":"蚂蚁百灵 Ling / Ring / Ming","en":"Ant Ling / Ring / Ming","pubZh":"蚂蚁集团 inclusionAI","pubEn":"Ant Group inclusionAI","origin":"cn","count":29,"variants":54,"latest":"2026-10-21","orgs":["inclusionAI"]},{"id":"lfm","zh":"Liquid LFM","en":"Liquid LFM","pubZh":"Liquid AI","pubEn":"Liquid AI","origin":"intl","count":26,"variants":138,"latest":"2026-10-12","orgs":["LiquidAI"]},{"id":"minicpm","zh":"面壁 MiniCPM / VoxCPM","en":"MiniCPM / VoxCPM","pubZh":"面壁智能 OpenBMB","pubEn":"OpenBMB","origin":"cn","count":23,"variants":75,"latest":"2026-10-07","orgs":["openbmb"]},{"id":"hunyuan","zh":"腾讯混元 Hunyuan / Hy","en":"Tencent Hunyuan / Hy","pubZh":"腾讯","pubEn":"Tencent","origin":"cn","count":19,"variants":56,"latest":"2026-10-15","orgs":["tencent"]},{"id":"phi","zh":"Phi","en":"Phi","pubZh":"微软","pubEn":"Microsoft","origin":"intl","count":18,"variants":28,"latest":"2026-01-23","orgs":["microsoft"]},{"id":"llama","zh":"Llama","en":"Llama","pubZh":"Meta","pubEn":"Meta","origin":"intl","count":16,"variants":34,"latest":"2025-04-28","orgs":["meta-llama"]},{"id":"longcat","zh":"美团 LongCat","en":"Meituan LongCat","pubZh":"美团","pubEn":"Meituan","origin":"cn","count":16,"variants":24,"latest":"2026-07-31","orgs":["meituan-longcat"]},{"id":"jina","zh":"Jina 向量与重排","en":"Jina embeddings & rerankers","pubZh":"Jina AI","pubEn":"Jina AI","origin":"intl","count":16,"variants":54,"latest":"2026-07-14","orgs":["jinaai"]},{"id":"wan","zh":"通义万相 Wan","en":"Wan","pubZh":"阿里巴巴通义万相","pubEn":"Alibaba Wan","origin":"cn","count":15,"variants":26,"latest":"2026-08-06","orgs":["Wan-AI"]},{"id":"kimi","zh":"Kimi","en":"Kimi","pubZh":"月之暗面","pubEn":"Moonshot AI","origin":"cn","count":14,"variants":17,"latest":"2026-06-13","orgs":["moonshotai"]},{"id":"cohere","zh":"Cohere Command / Aya","en":"Cohere Command / Aya","pubZh":"Cohere","pubEn":"Cohere","origin":"intl","count":14,"variants":19,"latest":"2026-08-10","orgs":["CohereLabs"]},{"id":"mimo","zh":"小米 MiMo","en":"Xiaomi MiMo","pubZh":"小米","pubEn":"Xiaomi","origin":"cn","count":14,"variants":18,"latest":"2026-09-27","orgs":["XiaomiMiMo"]},{"id":"flux","zh":"FLUX","en":"FLUX","pubZh":"Black Forest Labs","pubEn":"Black Forest Labs","origin":"intl","count":14,"variants":35,"latest":"2026-10-14","orgs":["black-forest-labs"]},{"id":"ms-other","zh":"微软 VibeVoice / Fara / Harrier","en":"Microsoft VibeVoice / Fara / Harrier","pubZh":"微软","pubEn":"Microsoft","origin":"intl","count":12,"variants":14,"latest":"2026-09-02","orgs":["microsoft"]},{"id":"internlm","zh":"书生 InternLM / Intern-S","en":"InternLM / Intern-S","pubZh":"上海人工智能实验室","pubEn":"Shanghai AI Lab","origin":"cn","count":12,"variants":28,"latest":"2026-09-13","orgs":["internlm"]},{"id":"step","zh":"阶跃星辰 Step","en":"StepFun Step","pubZh":"阶跃星辰","pubEn":"StepFun","origin":"cn","count":12,"variants":23,"latest":"2026-09-20","orgs":["stepfun-ai"]},{"id":"minimax","zh":"MiniMax","en":"MiniMax","pubZh":"MiniMax","pubEn":"MiniMax","origin":"cn","count":11,"variants":15,"latest":"2026-08-07","orgs":["MiniMaxAI"]},{"id":"ernie","zh":"百度文心 ERNIE","en":"Baidu ERNIE","pubZh":"百度","pubEn":"Baidu","origin":"cn","count":11,"variants":16,"latest":"2026-04-07","orgs":["baidu"]},{"id":"nv-speech","zh":"NVIDIA Parakeet / Canary 语音","en":"NVIDIA Parakeet / Canary speech","pubZh":"英伟达","pubEn":"NVIDIA","origin":"intl","count":10,"variants":10,"latest":"2026-04-07","orgs":["nvidia"]},{"id":"sd","zh":"Stable Diffusion / Stable Audio","en":"Stable Diffusion / Stable Audio","pubZh":"Stability AI","pubEn":"Stability AI","origin":"intl","count":10,"variants":18,"latest":"2026-05-17","orgs":["stabilityai"]},{"id":"yi","zh":"零一万物 Yi","en":"Yi (01.AI)","pubZh":"零一万物","pubEn":"01.AI","origin":"cn","count":9,"variants":13,"latest":"2024-08-21","orgs":["01-ai"]},{"id":"seed","zh":"字节 Seed","en":"ByteDance Seed","pubZh":"字节跳动 Seed","pubEn":"ByteDance Seed","origin":"cn","count":9,"variants":13,"latest":"2025-08-20","orgs":["ByteDance-Seed"]},{"id":"smollm","zh":"SmolLM / SmolVLM","en":"SmolLM / SmolVLM","pubZh":"Hugging Face","pubEn":"Hugging Face","origin":"intl","count":8,"variants":27,"latest":"2025-07-08","orgs":["HuggingFaceTB"]},{"id":"bge","zh":"BGE 向量与重排","en":"BGE embeddings & rerankers","pubZh":"智源 BAAI","pubEn":"BAAI","origin":"cn","count":8,"variants":8,"latest":"2025-05-15","orgs":["BAAI"]},{"id":"ltx","zh":"LTX 视频","en":"LTX Video","pubZh":"Lightricks","pubEn":"Lightricks","origin":"intl","count":8,"variants":11,"latest":"2026-07-23","orgs":["Lightricks"]},{"id":"funaudio","zh":"FunAudioLLM 语音","en":"FunAudioLLM speech","pubZh":"阿里通义实验室","pubEn":"Alibaba Tongyi Lab","origin":"cn","count":5,"variants":8,"latest":"2026-05-24","orgs":["FunAudioLLM"]},{"id":"gpt-oss","zh":"gpt-oss","en":"gpt-oss","pubZh":"OpenAI","pubEn":"OpenAI","origin":"intl","count":4,"variants":4,"latest":"2025-09-18","orgs":["openai"]},{"id":"laguna","zh":"poolside Laguna","en":"poolside Laguna","pubZh":"poolside","pubEn":"poolside","origin":"intl","count":4,"variants":26,"latest":"2026-07-13","orgs":["poolside"]},{"id":"whisper","zh":"Whisper","en":"Whisper","pubZh":"OpenAI","pubEn":"OpenAI","origin":"intl","count":2,"variants":2,"latest":"2024-10-01","orgs":["openai"]},{"id":"baichuan","zh":"百川 Baichuan","en":"Baichuan","pubZh":"百川智能","pubEn":"Baichuan","origin":"cn","count":2,"variants":7,"latest":"2026-01-13","orgs":["baichuan-inc"]},{"id":"inkling","zh":"Thinking Machines Inkling","en":"Thinking Machines Inkling","pubZh":"Thinking Machines Lab","pubEn":"Thinking Machines Lab","origin":"intl","count":2,"variants":4,"latest":"2026-07-27","orgs":["thinkingmachines"]},{"id":"grok","zh":"xAI Grok","en":"xAI Grok","pubZh":"xAI","pubEn":"xAI","origin":"intl","count":1,"variants":1,"latest":"2025-08-22","orgs":["xai-org"]},{"id":"dots","zh":"小红书 dots","en":"rednote dots","pubZh":"小红书 hi lab","pubEn":"rednote hi lab","origin":"cn","count":1,"variants":1,"latest":"2026-10-06","orgs":["rednote-hilab"]}],"hardware":[{"id":"gpu8","zh":"8GB 显卡","en":"8GB GPU","gb":8,"kind":"gpu"},{"id":"gpu12","zh":"12GB 显卡","en":"12GB GPU","gb":12,"kind":"gpu"},{"id":"gpu16","zh":"16GB 显卡","en":"16GB GPU","gb":16,"kind":"gpu"},{"id":"rtx4090","zh":"RTX 4090 24GB","en":"RTX 4090 24GB","gb":24,"kind":"gpu"},{"id":"rtx5090","zh":"RTX 5090 32GB","en":"RTX 5090 32GB","gb":32,"kind":"gpu"},{"id":"2x5090","zh":"2 × RTX 5090（64GB）","en":"2 × RTX 5090 (64GB)","gb":64,"kind":"gpu"},{"id":"h100","zh":"H100 80GB","en":"H100 80GB","gb":80,"kind":"gpu"},{"id":"pro6000","zh":"RTX PRO 6000 96GB","en":"RTX PRO 6000 96GB","gb":96,"kind":"gpu"},{"id":"h200","zh":"H200 141GB","en":"H200 141GB","gb":141,"kind":"gpu"},{"id":"4xpro6000","zh":"4 × RTX PRO 6000（384GB）","en":"4 × RTX PRO 6000 (384GB)","gb":384,"kind":"gpu"},{"id":"8xh100","zh":"8 × H100（640GB）","en":"8 × H100 (640GB)","gb":640,"kind":"gpu"},{"id":"8xh200","zh":"8 × H200（1,128GB）","en":"8 × H200 (1,128GB)","gb":1128,"kind":"gpu"},{"id":"8xb200","zh":"8 × B200（1,440GB）","en":"8 × B200 (1,440GB)","gb":1440,"kind":"gpu"},{"id":"8xb300","zh":"8 × B300（2,304GB）","en":"8 × B300 (2,304GB)","gb":2304,"kind":"gpu"},{"id":"2x8xb300","zh":"2 台 8 × B300（4,608GB）","en":"2 × 8 × B300 nodes (4,608GB)","gb":4608,"kind":"gpu"},{"id":"mac16","zh":"Mac 16GB","en":"Mac 16GB","gb":10.7,"kind":"mac"},{"id":"mac24","zh":"Mac 24GB","en":"Mac 24GB","gb":16,"kind":"mac"},{"id":"mac36","zh":"Mac 36GB","en":"Mac 36GB","gb":24,"kind":"mac"},{"id":"mac64","zh":"Mac 64GB","en":"Mac 64GB","gb":48,"kind":"mac"},{"id":"mac128","zh":"Mac 128GB","en":"Mac 128GB","gb":96,"kind":"mac"},{"id":"mac256","zh":"Mac 256GB","en":"Mac 256GB","gb":192,"kind":"mac"},{"id":"mac512","zh":"Mac 512GB","en":"Mac 512GB","gb":384,"kind":"mac"},{"id":"spark","zh":"DGX Spark 128GB","en":"DGX Spark 128GB","gb":115.2,"kind":"mac"}],"models":[{"id":"baichuan-m2-32b","name":"Baichuan-M2-32B","hf":"baichuan-inc/Baichuan-M2-32B","org":"baichuan-inc","family":"baichuan","series":"Baichuan-M2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-08-10","updated":"2025-12-24","gated":false,"params":{"total":32.764,"active":null,"src":"safetensors","q":null,"stTotal":32.764},"moe":false,"ctx":131072,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59,"131072":34.36},"mem":{"bf16":{"w":65.53,"t":74.7},"fp8":{"w":34.81,"t":40.9},"q4":{"w":19.86,"t":24.5}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":65.53,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baichuan-inc/Baichuan-M2-32B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"baichuan-inc/Baichuan-M2-32B","kind":"main"},{"id":"baichuan-inc/Baichuan-M2-32B-GPTQ-Int4","kind":"GPTQ/INT4"},{"id":"baichuan-inc/Baichuan-M2-32B-Q4_K_M-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · baichuan-inc/Baichuan-M2-32B","u":"https://huggingface.co/baichuan-inc/Baichuan-M2-32B"},{"t":"config.json","u":"https://huggingface.co/baichuan-inc/Baichuan-M2-32B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/baichuan-inc/Baichuan-M2-32B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/baichuan/#m-baichuan-m2-32b"},{"id":"baichuan-m3-235b","name":"Baichuan-M3-235B","hf":"baichuan-inc/Baichuan-M3-235B","org":"baichuan-inc","family":"baichuan","series":"Baichuan-M3","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-01-13","updated":"2026-02-09","gated":false,"params":{"total":235.094,"active":null,"src":"safetensors","q":null,"stTotal":235.094},"moe":true,"ctx":40960,"arch":{"L":94,"attn":94,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.58,"32768":6.31},"mem":{"bf16":{"w":470.19,"t":519.3},"fp8":{"w":249.79,"t":276.8},"q4":{"w":142.53,"t":158.9}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":470.19,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baichuan-inc/Baichuan-M3-235B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"baichuan-inc/Baichuan-M3-235B","kind":"main"},{"id":"baichuan-inc/Baichuan-M3-235B-GPTQ-INT4","kind":"GPTQ/INT4"},{"id":"baichuan-inc/Baichuan-M3-235B-FP8","kind":"FP8"},{"id":"baichuan-inc/Baichuan-M3-235B-Q4_K_M-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · baichuan-inc/Baichuan-M3-235B","u":"https://huggingface.co/baichuan-inc/Baichuan-M3-235B"},{"t":"config.json","u":"https://huggingface.co/baichuan-inc/Baichuan-M3-235B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/baichuan-inc/Baichuan-M3-235B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/baichuan-m3-235b/"},{"id":"bge-vl-base","name":"BGE-VL-base","hf":"BAAI/BGE-VL-base","org":"BAAI","family":"bge","series":"BGE-VL","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2025-02-25","updated":"2026-04-10","gated":false,"params":{"total":0.15,"active":null,"src":"safetensors","q":null,"stTotal":0.15},"moe":false,"ctx":77,"arch":null,"kv":null,"mem":{"bf16":{"w":0.3,"t":0.8},"fp8":{"w":0.16,"t":0.7},"q4":{"w":0.09,"t":0.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.3,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/BAAI/BGE-VL-base/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"BAAI/BGE-VL-base","kind":"Base"}],"sources":[{"t":"Hugging Face · BAAI/BGE-VL-base","u":"https://huggingface.co/BAAI/BGE-VL-base"},{"t":"config.json","u":"https://huggingface.co/BAAI/BGE-VL-base/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/BAAI/BGE-VL-base/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/bge/#m-bge-vl-base"},{"id":"bge-vl-large","name":"BGE-VL-large","hf":"BAAI/BGE-VL-large","org":"BAAI","family":"bge","series":"BGE-VL-large","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2025-02-25","updated":"2026-04-10","gated":false,"params":{"total":0.428,"active":null,"src":"safetensors","q":null,"stTotal":0.428},"moe":false,"ctx":77,"arch":null,"kv":null,"mem":{"bf16":{"w":0.86,"t":1.4},"fp8":{"w":0.45,"t":1},"q4":{"w":0.26,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.86,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/BAAI/BGE-VL-large/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"BAAI/BGE-VL-large","kind":"main"}],"sources":[{"t":"Hugging Face · BAAI/BGE-VL-large","u":"https://huggingface.co/BAAI/BGE-VL-large"},{"t":"config.json","u":"https://huggingface.co/BAAI/BGE-VL-large/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/BAAI/BGE-VL-large/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/bge/#m-bge-vl-large"},{"id":"bge-code-v1","name":"bge-code-v1","hf":"BAAI/bge-code-v1","org":"BAAI","family":"bge","series":"bge-code","task":"embedding","pipeline":"sentence-similarity","tags":["coding"],"released":"2025-05-15","updated":"2025-05-20","gated":false,"params":{"total":1.543,"active":null,"src":"safetensors","q":null,"stTotal":1.543},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":3.09,"t":3.9},"fp8":{"w":1.64,"t":2.3},"q4":{"w":0.94,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.17,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"BAAI/bge-code-v1","kind":"main"}],"sources":[{"t":"Hugging Face · BAAI/bge-code-v1","u":"https://huggingface.co/BAAI/bge-code-v1"},{"t":"config.json","u":"https://huggingface.co/BAAI/bge-code-v1/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/bge/#m-bge-code-v1"},{"id":"bge-en-icl","name":"bge-en-icl","hf":"BAAI/bge-en-icl","org":"BAAI","family":"bge","series":"bge-en-icl","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2024-07-25","updated":"2025-01-15","gated":false,"params":{"total":7.111,"active":null,"src":"safetensors","q":null,"stTotal":7.111},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":14.22,"t":16.1},"fp8":{"w":7.56,"t":8.8},"q4":{"w":4.31,"t":5.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":28.44,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"BAAI/bge-en-icl","kind":"main"}],"sources":[{"t":"Hugging Face · BAAI/bge-en-icl","u":"https://huggingface.co/BAAI/bge-en-icl"},{"t":"config.json","u":"https://huggingface.co/BAAI/bge-en-icl/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/bge/#m-bge-en-icl"},{"id":"bge-m3","name":"bge-m3","hf":"BAAI/bge-m3","org":"BAAI","family":"bge","series":"bge-m3","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2024-01-27","updated":"2024-07-03","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":8194,"arch":null,"kv":null,"mem":null,"fits":null,"disk":2.27,"native":null,"license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"bge-m3","url":"https://ollama.com/library/bge-m3"}],"variants":[{"id":"BAAI/bge-m3","kind":"main"}],"sources":[{"t":"Hugging Face · BAAI/bge-m3","u":"https://huggingface.co/BAAI/bge-m3"},{"t":"config.json","u":"https://huggingface.co/BAAI/bge-m3/blob/main/config.json"},{"t":"Ollama library · bge-m3","u":"https://ollama.com/library/bge-m3"}],"page":"https://aimap.page/en/models/compute/open-models/family/bge/#m-bge-m3"},{"id":"bge-multilingual-gemma2","name":"bge-multilingual-gemma2","hf":"BAAI/bge-multilingual-gemma2","org":"BAAI","family":"bge","series":"bge-multilingual-gemma2","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2024-07-25","updated":"2025-10-13","gated":false,"params":{"total":9.242,"active":null,"src":"safetensors","q":null,"stTotal":9.242},"moe":false,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":18.48,"t":20.8},"fp8":{"w":9.82,"t":11.3},"q4":{"w":5.6,"t":6.7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":36.97,"native":"F32","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"BAAI/bge-multilingual-gemma2","kind":"main"}],"sources":[{"t":"Hugging Face · BAAI/bge-multilingual-gemma2","u":"https://huggingface.co/BAAI/bge-multilingual-gemma2"},{"t":"config.json","u":"https://huggingface.co/BAAI/bge-multilingual-gemma2/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/bge/#m-bge-multilingual-gemma2"},{"id":"bge-reranker-v2-5-gemma2-lightweight","name":"bge-reranker-v2.5-gemma2-lightweight","hf":"BAAI/bge-reranker-v2.5-gemma2-lightweight","org":"BAAI","family":"bge","series":"bge-reranker-gemma2-lightweight","task":"rerank","pipeline":"text-classification","tags":[],"released":"2024-07-25","updated":"2024-09-06","gated":false,"params":{"total":9.242,"active":null,"src":"safetensors","q":null,"stTotal":9.242},"moe":false,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":18.48,"t":20.8},"fp8":{"w":9.82,"t":11.3},"q4":{"w":5.6,"t":6.7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":36.97,"native":"F32","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"BAAI/bge-reranker-v2.5-gemma2-lightweight","kind":"main"}],"sources":[{"t":"Hugging Face · BAAI/bge-reranker-v2.5-gemma2-lightweight","u":"https://huggingface.co/BAAI/bge-reranker-v2.5-gemma2-lightweight"},{"t":"config.json","u":"https://huggingface.co/BAAI/bge-reranker-v2.5-gemma2-lightweight/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/bge/#m-bge-reranker-v2-5-gemma2-lightweight"},{"id":"bge-reranker-v2-m3","name":"bge-reranker-v2-m3","hf":"BAAI/bge-reranker-v2-m3","org":"BAAI","family":"bge","series":"bge-reranker-m3","task":"rerank","pipeline":"text-classification","tags":[],"released":"2024-03-15","updated":"2024-06-24","gated":false,"params":{"total":0.568,"active":null,"src":"safetensors","q":null,"stTotal":0.568},"moe":false,"ctx":8194,"arch":null,"kv":null,"mem":{"bf16":{"w":1.14,"t":1.7},"fp8":{"w":0.6,"t":1.2},"q4":{"w":0.34,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.27,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"BAAI/bge-reranker-v2-m3","kind":"main"}],"sources":[{"t":"Hugging Face · BAAI/bge-reranker-v2-m3","u":"https://huggingface.co/BAAI/bge-reranker-v2-m3"},{"t":"config.json","u":"https://huggingface.co/BAAI/bge-reranker-v2-m3/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/bge/#m-bge-reranker-v2-m3"},{"id":"north-micro-vision-instruct","name":"North-Micro-Vision-Instruct","hf":"CohereLabs/North-Micro-Vision-Instruct","org":"CohereLabs","family":"cohere","series":"North-Micro-Vision","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-08-10","updated":"2026-09-30","gated":false,"params":{"total":2.485,"active":null,"src":"safetensors","q":null,"stTotal":2.485},"moe":false,"ctx":500000,"arch":{"L":28,"attn":7,"slide":21,"win":4096,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.59,"32768":1.29,"131072":4.11},"mem":{"bf16":{"w":4.97,"t":6.6},"fp8":{"w":2.64,"t":4},"q4":{"w":1.51,"t":2.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.97,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"CohereLabs/North-Micro-Vision-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · CohereLabs/North-Micro-Vision-Instruct","u":"https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct"},{"t":"config.json","u":"https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/cohere/#m-north-micro-vision-instruct"},{"id":"north-mini-code-1-0","name":"North-Mini-Code-1.0","hf":"CohereLabs/North-Mini-Code-1.0","org":"CohereLabs","family":"cohere","series":"North-Mini-Code-1.0","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2026-06-05","updated":"2026-06-15","gated":false,"params":{"total":30,"active":3,"src":"card","q":"Model Size: 30B total; 3B active","stTotal":30.484},"moe":true,"ctx":500000,"arch":{"L":49,"attn":13,"slide":36,"win":4096,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.52,"32768":1.17,"131072":3.79},"mem":{"bf16":{"w":60,"t":67},"fp8":{"w":31.88,"t":36.1},"q4":{"w":18.19,"t":21}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":60.97,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"north-mini-code-1.0","url":"https://ollama.com/library/north-mini-code-1.0"}],"variants":[{"id":"CohereLabs/North-Mini-Code-1.0","kind":"main"},{"id":"CohereLabs/North-Mini-Code-1.0-w4a16","kind":"W4A16"},{"id":"CohereLabs/North-Mini-Code-1.0-fp8","kind":"FP8"}],"sources":[{"t":"Hugging Face · CohereLabs/North-Mini-Code-1.0","u":"https://huggingface.co/CohereLabs/North-Mini-Code-1.0"},{"t":"config.json","u":"https://huggingface.co/CohereLabs/North-Mini-Code-1.0/blob/main/config.json"},{"t":"Ollama library · north-mini-code-1.0","u":"https://ollama.com/library/north-mini-code-1.0"}],"page":"https://aimap.page/en/models/compute/open-models/family/cohere/#m-north-mini-code-1-0"},{"id":"aya-23-8b","name":"aya-23-8B","hf":"CohereLabs/aya-23-8B","org":"CohereLabs","family":"cohere","series":"aya-23","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-19","updated":"2025-09-11","gated":true,"params":{"total":8.028,"active":null,"src":"safetensors","q":null,"stTotal":8.028},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":16.06,"t":18.2},"fp8":{"w":8.53,"t":9.9},"q4":{"w":4.87,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.06,"native":"F16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"CohereLabs/aya-23-8B","kind":"main"}],"sources":[{"t":"Hugging Face · CohereLabs/aya-23-8B","u":"https://huggingface.co/CohereLabs/aya-23-8B"}],"page":"https://aimap.page/en/models/compute/open-models/family/cohere/#m-aya-23-8b"},{"id":"aya-expanse-8b","name":"aya-expanse-8b","hf":"CohereLabs/aya-expanse-8b","org":"CohereLabs","family":"cohere","series":"aya-expanse","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-10-23","updated":"2026-01-09","gated":true,"params":{"total":8.028,"active":null,"src":"safetensors","q":null,"stTotal":8.028},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":16.06,"t":18.2},"fp8":{"w":8.53,"t":9.9},"q4":{"w":4.87,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.06,"native":"F16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"aya-expanse:8b","url":"https://ollama.com/library/aya-expanse"}],"variants":[{"id":"CohereLabs/aya-expanse-8b","kind":"main"}],"sources":[{"t":"Hugging Face · CohereLabs/aya-expanse-8b","u":"https://huggingface.co/CohereLabs/aya-expanse-8b"},{"t":"Ollama library · aya-expanse","u":"https://ollama.com/library/aya-expanse"}],"page":"https://aimap.page/en/models/compute/open-models/family/cohere/#m-aya-expanse-8b"},{"id":"aya-expanse-32b","name":"aya-expanse-32b","hf":"CohereLabs/aya-expanse-32b","org":"CohereLabs","family":"cohere","series":"aya-expanse","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-10-23","updated":"2026-01-09","gated":true,"params":{"total":32.296,"active":null,"src":"safetensors","q":null,"stTotal":32.296},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":64.59,"t":71.6},"fp8":{"w":34.31,"t":38.2},"q4":{"w":19.58,"t":22}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":64.59,"native":"F16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"aya-expanse:32b","url":"https://ollama.com/library/aya-expanse"}],"variants":[{"id":"CohereLabs/aya-expanse-32b","kind":"main"}],"sources":[{"t":"Hugging Face · CohereLabs/aya-expanse-32b","u":"https://huggingface.co/CohereLabs/aya-expanse-32b"},{"t":"Ollama library · aya-expanse","u":"https://ollama.com/library/aya-expanse"}],"page":"https://aimap.page/en/models/compute/open-models/family/cohere/#m-aya-expanse-32b"},{"id":"aya-vision-8b","name":"aya-vision-8b","hf":"CohereLabs/aya-vision-8b","org":"CohereLabs","family":"cohere","series":"aya-vision","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-03-02","updated":"2026-01-09","gated":true,"params":{"total":8.632,"active":null,"src":"safetensors","q":null,"stTotal":8.632},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":17.26,"t":19.5},"fp8":{"w":9.17,"t":10.6},"q4":{"w":5.23,"t":6.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.26,"native":"F16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"CohereLabs/aya-vision-8b","kind":"main"}],"sources":[{"t":"Hugging Face · CohereLabs/aya-vision-8b","u":"https://huggingface.co/CohereLabs/aya-vision-8b"}],"page":"https://aimap.page/en/models/compute/open-models/family/cohere/#m-aya-vision-8b"},{"id":"c4ai-command-a-03-2025","name":"c4ai-command-a-03-2025","hf":"CohereLabs/c4ai-command-a-03-2025","org":"CohereLabs","family":"cohere","series":"c4ai-command-a","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-03-11","updated":"2025-10-30","gated":true,"params":{"total":111.058,"active":null,"src":"safetensors","q":null,"stTotal":111.058},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":222.12,"t":244.8},"fp8":{"w":118,"t":130.3},"q4":{"w":67.33,"t":74.6}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":222.12,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"CohereLabs/c4ai-command-a-03-2025","kind":"main"}],"sources":[{"t":"Hugging Face · CohereLabs/c4ai-command-a-03-2025","u":"https://huggingface.co/CohereLabs/c4ai-command-a-03-2025"}],"page":"https://aimap.page/en/models/compute/open-models/c4ai-command-a-03-2025/"},{"id":"c4ai-command-r7b-12-2024","name":"c4ai-command-r7b-12-2024","hf":"CohereLabs/c4ai-command-r7b-12-2024","org":"CohereLabs","family":"cohere","series":"c4ai-command-r7b","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-12-11","updated":"2025-10-30","gated":true,"params":{"total":8.028,"active":null,"src":"safetensors","q":null,"stTotal":8.028},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":16.06,"t":18.2},"fp8":{"w":8.53,"t":9.9},"q4":{"w":4.87,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.06,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"CohereLabs/c4ai-command-r7b-12-2024","kind":"main"}],"sources":[{"t":"Hugging Face · CohereLabs/c4ai-command-r7b-12-2024","u":"https://huggingface.co/CohereLabs/c4ai-command-r7b-12-2024"}],"page":"https://aimap.page/en/models/compute/open-models/family/cohere/#m-c4ai-command-r7b-12-2024"},{"id":"c4ai-command-r7b-arabic-02-2025","name":"c4ai-command-r7b-arabic-02-2025","hf":"CohereLabs/c4ai-command-r7b-arabic-02-2025","org":"CohereLabs","family":"cohere","series":"c4ai-command-r7b-arabic","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-02-27","updated":"2025-10-30","gated":true,"params":{"total":8.028,"active":null,"src":"safetensors","q":null,"stTotal":8.028},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":16.06,"t":18.2},"fp8":{"w":8.53,"t":9.9},"q4":{"w":4.87,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.06,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"CohereLabs/c4ai-command-r7b-arabic-02-2025","kind":"main"}],"sources":[{"t":"Hugging Face · CohereLabs/c4ai-command-r7b-arabic-02-2025","u":"https://huggingface.co/CohereLabs/c4ai-command-r7b-arabic-02-2025"}],"page":"https://aimap.page/en/models/compute/open-models/family/cohere/#m-c4ai-command-r7b-arabic-02-2025"},{"id":"command-a-plus-05-2026-bf16","name":"command-a-plus-05-2026-bf16","hf":"CohereLabs/command-a-plus-05-2026-bf16","org":"CohereLabs","family":"cohere","series":"command-a-plus","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-05-11","updated":"2026-06-15","gated":false,"params":{"total":218,"active":25,"src":"card","q":"25B active parameters, 218B total parameters","stTotal":218.75},"moe":true,"ctx":200000,"arch":{"L":32,"attn":8,"slide":24,"win":4096,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":1.48,"131072":4.7},"mem":{"bf16":{"w":436,"t":480.8},"fp8":{"w":231.62,"t":256},"q4":{"w":132.16,"t":146.5}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":437.5,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"CohereLabs/command-a-plus-05-2026-bf16","kind":"BF16"},{"id":"CohereLabs/command-a-plus-05-2026-w4a4","kind":"main"},{"id":"CohereLabs/command-a-plus-05-2026-fp8","kind":"FP8"}],"sources":[{"t":"Hugging Face · CohereLabs/command-a-plus-05-2026-bf16","u":"https://huggingface.co/CohereLabs/command-a-plus-05-2026-bf16"},{"t":"config.json","u":"https://huggingface.co/CohereLabs/command-a-plus-05-2026-bf16/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/command-a-plus-05-2026-bf16/"},{"id":"command-a-reasoning-08-2025","name":"command-a-reasoning-08-2025","hf":"CohereLabs/command-a-reasoning-08-2025","org":"CohereLabs","family":"cohere","series":"command-a-reasoning","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-08-12","updated":"2026-01-13","gated":true,"params":{"total":111.058,"active":null,"src":"safetensors","q":null,"stTotal":111.058},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":222.12,"t":244.8},"fp8":{"w":118,"t":130.3},"q4":{"w":67.33,"t":74.6}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":222.12,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"CohereLabs/command-a-reasoning-08-2025","kind":"main"}],"sources":[{"t":"Hugging Face · CohereLabs/command-a-reasoning-08-2025","u":"https://huggingface.co/CohereLabs/command-a-reasoning-08-2025"}],"page":"https://aimap.page/en/models/compute/open-models/command-a-reasoning-08-2025/"},{"id":"command-a-vision-07-2025","name":"command-a-vision-07-2025","hf":"CohereLabs/command-a-vision-07-2025","org":"CohereLabs","family":"cohere","series":"command-a-vision","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-07-28","updated":"2025-10-30","gated":true,"params":{"total":111.868,"active":null,"src":"safetensors","q":null,"stTotal":111.868},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":223.74,"t":246.6},"fp8":{"w":118.86,"t":131.2},"q4":{"w":67.82,"t":75.1}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":223.74,"native":"F16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"CohereLabs/command-a-vision-07-2025","kind":"main"}],"sources":[{"t":"Hugging Face · CohereLabs/command-a-vision-07-2025","u":"https://huggingface.co/CohereLabs/command-a-vision-07-2025"}],"page":"https://aimap.page/en/models/compute/open-models/command-a-vision-07-2025/"},{"id":"tiny-aya-base","name":"tiny-aya-base","hf":"CohereLabs/tiny-aya-base","org":"CohereLabs","family":"cohere","series":"tiny-aya","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-02-13","updated":"2026-09-30","gated":true,"params":{"total":3.349,"active":null,"src":"safetensors","q":null,"stTotal":3.349},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":6.7,"t":7.9},"fp8":{"w":3.56,"t":4.4},"q4":{"w":2.03,"t":2.7}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.7,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"CohereLabs/tiny-aya-base","kind":"Base"}],"sources":[{"t":"Hugging Face · CohereLabs/tiny-aya-base","u":"https://huggingface.co/CohereLabs/tiny-aya-base"}],"page":"https://aimap.page/en/models/compute/open-models/family/cohere/#m-tiny-aya-base"},{"id":"tiny-aya-global","name":"tiny-aya-global","hf":"CohereLabs/tiny-aya-global","org":"CohereLabs","family":"cohere","series":"tiny-aya-global","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-02-13","updated":"2026-09-30","gated":true,"params":{"total":3.349,"active":null,"src":"safetensors","q":null,"stTotal":3.349},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":6.7,"t":7.9},"fp8":{"w":3.56,"t":4.4},"q4":{"w":2.03,"t":2.7}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.7,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"CohereLabs/tiny-aya-global","kind":"main"},{"id":"CohereLabs/tiny-aya-global-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · CohereLabs/tiny-aya-global","u":"https://huggingface.co/CohereLabs/tiny-aya-global"}],"page":"https://aimap.page/en/models/compute/open-models/family/cohere/#m-tiny-aya-global"},{"id":"deepseek-v2-chat-0628","name":"DeepSeek-V2-Chat-0628","hf":"deepseek-ai/DeepSeek-V2-Chat-0628","org":"deepseek-ai","family":"deepseek","series":"DeepSeek","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-07-18","updated":"2024-07-18","gated":false,"params":{"total":235.741,"active":null,"src":"safetensors","q":null,"stTotal":235.741},"moe":true,"ctx":163840,"arch":{"L":60,"attn":60,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.57,"32768":2.26,"131072":9.06},"mem":{"bf16":{"w":471.48,"t":519.7},"fp8":{"w":250.47,"t":276.6},"q4":{"w":142.92,"t":158.3}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":471.49,"native":"BF16","license":{"id":"deepseek","name":"deepseek","link":"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V2-Chat-0628","kind":"Instruct"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V2-Chat-0628","u":"https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat-0628"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat-0628/blob/main/config.json"},{"t":"License","u":"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v2-chat-0628/"},{"id":"deepseek-v2-5-1210","name":"DeepSeek-V2.5-1210","hf":"deepseek-ai/DeepSeek-V2.5-1210","org":"deepseek-ai","family":"deepseek","series":"DeepSeek","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-12-10","updated":"2024-12-11","gated":false,"params":{"total":235.741,"active":null,"src":"safetensors","q":null,"stTotal":235.741},"moe":true,"ctx":163840,"arch":{"L":60,"attn":60,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.57,"32768":2.26,"131072":9.06},"mem":{"bf16":{"w":471.48,"t":519.7},"fp8":{"w":250.47,"t":276.6},"q4":{"w":142.92,"t":158.3}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":471.49,"native":"BF16","license":{"id":"deepseek","name":"deepseek","link":"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V2.5-1210","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V2.5-1210","u":"https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210/blob/main/config.json"},{"t":"License","u":"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v2-5-1210/"},{"id":"deepseek-v2-5","name":"DeepSeek-V2.5","hf":"deepseek-ai/DeepSeek-V2.5","org":"deepseek-ai","family":"deepseek","series":"DeepSeek","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-05","updated":"2024-12-11","gated":false,"params":{"total":235.741,"active":null,"src":"safetensors","q":null,"stTotal":235.741},"moe":true,"ctx":163840,"arch":{"L":60,"attn":60,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.57,"32768":2.26,"131072":9.06},"mem":{"bf16":{"w":471.48,"t":519.7},"fp8":{"w":250.47,"t":276.6},"q4":{"w":142.92,"t":158.3}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":471.49,"native":"BF16","license":{"id":"deepseek","name":"deepseek","link":"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"deepseek-v2.5","url":"https://ollama.com/library/deepseek-v2.5"}],"variants":[{"id":"deepseek-ai/DeepSeek-V2.5","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V2.5","u":"https://huggingface.co/deepseek-ai/DeepSeek-V2.5"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V2.5/blob/main/config.json"},{"t":"License","u":"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL"},{"t":"Ollama library · deepseek-v2.5","u":"https://ollama.com/library/deepseek-v2.5"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v2-5/"},{"id":"deepseek-v3-1-base","name":"DeepSeek-V3.1-Base","hf":"deepseek-ai/DeepSeek-V3.1-Base","org":"deepseek-ai","family":"deepseek","series":"DeepSeek","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-08-19","updated":"2025-08-26","gated":false,"params":{"total":671,"active":37,"src":"card","q":"| DeepSeek-V3.1-Base | 671B | 37B | 128K |","stTotal":684.531},"moe":true,"ctx":163840,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":1342,"t":1477.3},"fp8":{"w":712.94,"t":785.3},"q4":{"w":406.79,"t":448.6}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":688.59,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Base/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V3.1","kind":"main"},{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","kind":"main"},{"id":"deepseek-ai/DeepSeek-V3.1-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V3.1-Base","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Base"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Base/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Base/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v3-1-base/"},{"id":"deepseek-v3","name":"DeepSeek-V3","hf":"deepseek-ai/DeepSeek-V3","org":"deepseek-ai","family":"deepseek","series":"DeepSeek","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-12-25","updated":"2025-03-27","gated":false,"params":{"total":671,"active":37,"src":"card","q":"671B total parameters with 37B activated for each token","stTotal":684.49},"moe":true,"ctx":163840,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":1342,"t":1477.3},"fp8":{"w":712.94,"t":785.3},"q4":{"w":406.79,"t":448.6}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":688.59,"native":"F8_E4M3","license":{"id":null,"name":null,"link":null,"cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"},{"id":"lmdeploy","via":"card"},{"id":"ollama","via":"ollama-library","tag":"deepseek-v3","url":"https://ollama.com/library/deepseek-v3"}],"variants":[{"id":"deepseek-ai/DeepSeek-V3","kind":"main"},{"id":"deepseek-ai/DeepSeek-V3-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V3","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3/blob/main/config.json"},{"t":"Ollama library · deepseek-v3","u":"https://ollama.com/library/deepseek-v3"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v3/"},{"id":"deepseek-v3-0324","name":"DeepSeek-V3-0324","hf":"deepseek-ai/DeepSeek-V3-0324","org":"deepseek-ai","family":"deepseek","series":"DeepSeek","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-03-24","updated":"2025-03-27","gated":false,"params":{"total":684.531,"active":null,"src":"safetensors","q":null,"stTotal":684.531},"moe":true,"ctx":163840,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":1369.06,"t":1507},"fp8":{"w":727.31,"t":801.1},"q4":{"w":415,"t":457.6}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":688.59,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V3-0324","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V3-0324","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v3-0324/"},{"id":"deepseek-v3-2","name":"DeepSeek-V3.2","hf":"deepseek-ai/DeepSeek-V3.2","org":"deepseek-ai","family":"deepseek","series":"DeepSeek","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-12-01","updated":"2025-12-01","gated":false,"params":{"total":685.355,"active":null,"src":"safetensors","q":null,"stTotal":685.355},"moe":true,"ctx":163840,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":1370.71,"t":1508.9},"fp8":{"w":728.19,"t":802.1},"q4":{"w":415.5,"t":458.1}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":689.48,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V3.2","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V3.2","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v3-2/"},{"id":"deepseek-coder-v2-instruct-0724","name":"DeepSeek-Coder-V2-Instruct-0724","hf":"deepseek-ai/DeepSeek-Coder-V2-Instruct-0724","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-09-05","updated":"2024-10-08","gated":false,"params":{"total":236,"active":21,"src":"card","q":"DeepSeek-Coder-V2 with 16B and 236B parameters … actived parameters of only 2.4B and 21B","stTotal":235.741},"moe":true,"ctx":163840,"arch":{"L":60,"attn":60,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.57,"32768":2.26,"131072":9.06},"mem":{"bf16":{"w":472,"t":520.3},"fp8":{"w":250.75,"t":276.9},"q4":{"w":143.07,"t":158.5}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":471.49,"native":"BF16","license":{"id":"deepseek-license","name":"deepseek-license","link":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct-0724/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-Coder-V2-Instruct-0724","kind":"Instruct"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-Coder-V2-Instruct-0724","u":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct-0724"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct-0724/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct-0724/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-coder-v2-instruct-0724/"},{"id":"deepseek-coder-v2-instruct","name":"DeepSeek-Coder-V2-Instruct","hf":"deepseek-ai/DeepSeek-Coder-V2-Instruct","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-06-14","updated":"2024-08-21","gated":false,"params":{"total":236,"active":21,"src":"card","q":"DeepSeek-Coder-V2 with 16B and 236B parameters … actived parameters of only 2.4B and 21B","stTotal":235.741},"moe":true,"ctx":163840,"arch":{"L":60,"attn":60,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.57,"32768":2.26,"131072":9.06},"mem":{"bf16":{"w":472,"t":520.3},"fp8":{"w":250.75,"t":276.9},"q4":{"w":143.07,"t":158.5}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":471.49,"native":"BF16","license":{"id":"deepseek-license","name":"deepseek-license","link":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"deepseek-coder-v2","url":"https://ollama.com/library/deepseek-coder-v2"}],"variants":[{"id":"deepseek-ai/DeepSeek-Coder-V2-Instruct","kind":"Instruct"},{"id":"deepseek-ai/DeepSeek-Coder-V2-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-Coder-V2-Instruct","u":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct/blob/main/LICENSE"},{"t":"Ollama library · deepseek-coder-v2","u":"https://ollama.com/library/deepseek-coder-v2"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-coder-v2-instruct/"},{"id":"deepseek-coder-v2-lite-instruct","name":"DeepSeek-Coder-V2-Lite-Instruct","hf":"deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Coder-Lite","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-06-14","updated":"2024-07-03","gated":false,"params":{"total":16,"active":2.4,"src":"card","q":"DeepSeek-Coder-V2 with 16B and 236B parameters … actived parameters of only 2.4B and 21B","stTotal":15.706},"moe":true,"ctx":163840,"arch":{"L":27,"attn":27,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.25,"32768":1.02,"131072":4.08},"mem":{"bf16":{"w":32,"t":36},"fp8":{"w":17,"t":19.5},"q4":{"w":9.7,"t":11.4}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":31.41,"native":"BF16","license":{"id":"deepseek-license","name":"deepseek-license","link":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct","kind":"Instruct"},{"id":"deepseek-ai/DeepSeek-Coder-V2-Lite-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct","u":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-coder-v2-lite-instruct"},{"id":"deepseek-v3-2-exp-base","name":"DeepSeek-V3.2-Exp-Base","hf":"deepseek-ai/DeepSeek-V3.2-Exp-Base","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Exp","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-29","updated":"2025-10-09","gated":false,"params":{"total":685.355,"active":null,"src":"safetensors","q":null,"stTotal":685.355},"moe":true,"ctx":163840,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":1370.71,"t":1508.9},"fp8":{"w":728.19,"t":802.1},"q4":{"w":415.5,"t":458.1}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":689.48,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp-Base/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V3.2-Exp-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V3.2-Exp-Base","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp-Base"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp-Base/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp-Base/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v3-2-exp-base/"},{"id":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","hf":"deepseek-ai/DeepSeek-V4-Flash","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Flash","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-22","updated":"2026-06-22","gated":false,"params":{"total":284,"active":13,"src":"card","q":"DeepSeek-V4-Flash with 284B parameters (13B activated)","stTotal":290.945},"moe":true,"ctx":1048576,"arch":{"L":43,"attn":43,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":["compress_ratios"]},"kv":null,"mem":{"bf16":{"w":568,"t":625.3},"fp8":{"w":301.75,"t":332.4},"q4":{"w":172.17,"t":189.9}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":159.62,"native":"I8","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V4-Flash","kind":"main"},{"id":"deepseek-ai/DeepSeek-V4-Flash-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V4-Flash","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v4-flash/"},{"id":"deepseek-v4-flash-0731","name":"DeepSeek-V4-Flash-0731","hf":"deepseek-ai/DeepSeek-V4-Flash-0731","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Flash","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-07-31","updated":"2026-08-01","gated":false,"params":{"total":304.18,"active":null,"src":"safetensors-packed","q":null,"stTotal":304.18},"moe":true,"ctx":1048576,"arch":{"L":43,"attn":43,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":["compress_ratios"]},"kv":null,"mem":{"bf16":{"w":608.36,"t":669.7},"fp8":{"w":323.19,"t":356},"q4":{"w":184.41,"t":203.4}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":166.89,"native":"I8","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V4-Flash-0731","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v4-flash-0731/"},{"id":"deepseek-v4-1-flash-1017","name":"DeepSeek-V4.1-Flash-1017","hf":"deepseek-ai/DeepSeek-V4.1-Flash-1017","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Flash","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-10-17","updated":"2026-10-17","gated":false,"params":{"total":748,"active":16,"src":"card","q":"Same architecture as DeepSeek-V4.1-Flash per its card: 552B backbone + 196B Engram; 8B (prefill) / 16B (decode) activated","stTotal":763.205},"moe":true,"ctx":1048576,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":["compress_ratios","kv_source_layer_ids"]},"kv":null,"mem":{"bf16":{"w":1496,"t":1646.1},"fp8":{"w":794.75,"t":874.7},"q4":{"w":453.47,"t":499.3}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":510.3,"native":"I8","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V4.1-Flash-1017","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v4-1-flash-1017/"},{"id":"deepseek-v4-1-flash","name":"DeepSeek-V4.1-Flash","hf":"deepseek-ai/DeepSeek-V4.1-Flash","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Flash","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-09-10","updated":"2026-10-16","gated":false,"params":{"total":748,"active":16,"src":"card","q":"552B backbone parameters … Engram conditional memory (196B parameters) … activate only 8B parameters per token during prefill and 16B during decode","stTotal":763.205},"moe":true,"ctx":1048576,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":["compress_ratios","kv_source_layer_ids"]},"kv":null,"mem":{"bf16":{"w":1496,"t":1646.1},"fp8":{"w":794.75,"t":874.7},"q4":{"w":453.47,"t":499.3}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":510.3,"native":"I8","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V4.1-Flash","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V4.1-Flash","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v4-1-flash/"},{"id":"deepseek-v2-lite","name":"DeepSeek-V2-Lite","hf":"deepseek-ai/DeepSeek-V2-Lite","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Lite","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-15","updated":"2024-06-25","gated":false,"params":{"total":16,"active":2.4,"src":"card","q":"16B total params, 2.4B active params","stTotal":15.706},"moe":true,"ctx":163840,"arch":{"L":27,"attn":27,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.25,"32768":1.02,"131072":4.08},"mem":{"bf16":{"w":32,"t":36},"fp8":{"w":17,"t":19.5},"q4":{"w":9.7,"t":11.4}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":31.41,"native":"BF16","license":{"id":"deepseek","name":"deepseek","link":"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V2-Lite","kind":"main"},{"id":"deepseek-ai/DeepSeek-V2-Lite-Chat","kind":"Instruct"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V2-Lite","u":"https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite/blob/main/config.json"},{"t":"License","u":"https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-v2-lite"},{"id":"deepseek-ocr","name":"DeepSeek-OCR","hf":"deepseek-ai/DeepSeek-OCR","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-OCR","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2025-10-17","updated":"2025-11-04","gated":false,"params":{"total":3.336,"active":null,"src":"safetensors","q":null,"stTotal":3.336},"moe":true,"ctx":8192,"arch":{"L":12,"attn":12,"slide":0,"win":null,"kvElems":2560,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.5},"mem":{"bf16":{"w":6.67,"t":8.3},"fp8":{"w":3.54,"t":4.9},"q4":{"w":2.02,"t":3.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.67,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-OCR/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"deepseek-ocr","url":"https://ollama.com/library/deepseek-ocr"}],"variants":[{"id":"deepseek-ai/DeepSeek-OCR","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-OCR","u":"https://huggingface.co/deepseek-ai/DeepSeek-OCR"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-OCR/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-OCR/blob/main/LICENSE"},{"t":"Ollama library · deepseek-ocr","u":"https://ollama.com/library/deepseek-ocr"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-ocr"},{"id":"deepseek-ocr-2","name":"DeepSeek-OCR-2","hf":"deepseek-ai/DeepSeek-OCR-2","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-OCR-2","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2026-01-27","updated":"2026-02-03","gated":false,"params":{"total":3.389,"active":null,"src":"safetensors","q":null,"stTotal":3.389},"moe":true,"ctx":8192,"arch":{"L":12,"attn":12,"slide":0,"win":null,"kvElems":2560,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.5},"mem":{"bf16":{"w":6.78,"t":8.5},"fp8":{"w":3.6,"t":5},"q4":{"w":2.05,"t":3.3}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.78,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/deepseek-ai/DeepSeek-OCR-2/blob/main/LICENSE.txt","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-OCR-2","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-OCR-2","u":"https://huggingface.co/deepseek-ai/DeepSeek-OCR-2"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-OCR-2/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-OCR-2/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-ocr-2"},{"id":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","hf":"deepseek-ai/DeepSeek-V4-Pro","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Pro","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-22","updated":"2026-06-22","gated":false,"params":{"total":1600,"active":49,"src":"card","q":"DeepSeek-V4-Pro with 1.6T parameters (49B activated)","stTotal":1598.84},"moe":true,"ctx":1048576,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":["compress_ratios"]},"kv":null,"mem":{"bf16":{"w":3200,"t":3520.5},"fp8":{"w":1700,"t":1870.5},"q4":{"w":970,"t":1067.5}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb300","mac":null},"q4":{"gpu":"8xb200","mac":null}},"disk":864.72,"native":"I8","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V4-Pro","kind":"main"},{"id":"deepseek-ai/DeepSeek-V4-Pro-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V4-Pro","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v4-pro/"},{"id":"deepseek-v4-pro-0813","name":"DeepSeek-V4-Pro-0813","hf":"deepseek-ai/DeepSeek-V4-Pro-0813","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Pro","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-08-13","updated":"2026-08-13","gated":false,"params":{"total":1650.498,"active":null,"src":"safetensors-packed","q":null,"stTotal":1650.498},"moe":true,"ctx":1048576,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":["compress_ratios"]},"kv":null,"mem":{"bf16":{"w":3301,"t":3631.6},"fp8":{"w":1753.65,"t":1929.5},"q4":{"w":1000.61,"t":1101.2}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb300","mac":null},"q4":{"gpu":"8xb200","mac":null}},"disk":892.74,"native":"I8","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V4-Pro-0813","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v4-pro-0813/"},{"id":"deepseek-r1","name":"DeepSeek-R1","hf":"deepseek-ai/DeepSeek-R1","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-R1","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-01-20","updated":"2025-03-27","gated":false,"params":{"total":671,"active":37,"src":"card","q":"#Total Params 671B, #Activated Params 37B","stTotal":684.49},"moe":true,"ctx":163840,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":1342,"t":1477.3},"fp8":{"w":712.94,"t":785.3},"q4":{"w":406.79,"t":448.6}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":688.59,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-R1/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"deepseek-r1","url":"https://ollama.com/library/deepseek-r1"}],"variants":[{"id":"deepseek-ai/DeepSeek-R1","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-R1","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1/blob/main/LICENSE"},{"t":"Ollama library · deepseek-r1","u":"https://ollama.com/library/deepseek-r1"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-r1/"},{"id":"deepseek-r1-0528","name":"DeepSeek-R1-0528","hf":"deepseek-ai/DeepSeek-R1-0528","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-R1","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-05-28","updated":"2025-05-29","gated":false,"params":{"total":684.531,"active":null,"src":"safetensors","q":null,"stTotal":684.531},"moe":true,"ctx":163840,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":1369.06,"t":1507},"fp8":{"w":727.31,"t":801.1},"q4":{"w":415,"t":457.6}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":688.59,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-R1-0528","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-R1-0528","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-r1-0528/"},{"id":"deepseek-r1-distill-llama-8b","name":"DeepSeek-R1-Distill-Llama-8B","hf":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-R1-Distill-Llama","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-01-20","updated":"2025-02-24","gated":false,"params":{"total":8.03,"active":null,"src":"safetensors","q":null,"stTotal":8.03},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":16.06,"t":19.2},"fp8":{"w":8.53,"t":11},"q4":{"w":4.87,"t":6.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.06,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-R1-Distill-Llama-8B","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-r1-distill-llama-8b"},{"id":"deepseek-r1-distill-llama-70b","name":"DeepSeek-R1-Distill-Llama-70B","hf":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-R1-Distill-Llama","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-01-20","updated":"2025-02-24","gated":false,"params":{"total":70.554,"active":null,"src":"safetensors","q":null,"stTotal":70.554},"moe":false,"ctx":131072,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74,"131072":42.95},"mem":{"bf16":{"w":141.11,"t":158.4},"fp8":{"w":74.96,"t":85.6},"q4":{"w":42.77,"t":50.2}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"pro6000","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":141.11,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-R1-Distill-Llama-70B","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-r1-distill-llama-70b"},{"id":"deepseek-r1-distill-qwen-1-5b","name":"DeepSeek-R1-Distill-Qwen-1.5B","hf":"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-R1-Distill-Qwen","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-01-20","updated":"2025-02-24","gated":false,"params":{"total":1.777,"active":null,"src":"safetensors","q":null,"stTotal":1.777},"moe":false,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.23,"32768":0.94,"131072":3.76},"mem":{"bf16":{"w":3.55,"t":4.6},"fp8":{"w":1.89,"t":2.8},"q4":{"w":1.08,"t":1.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.55,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-r1-distill-qwen-1-5b"},{"id":"deepseek-r1-distill-qwen-7b","name":"DeepSeek-R1-Distill-Qwen-7B","hf":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-R1-Distill-Qwen","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-01-20","updated":"2025-02-24","gated":false,"params":{"total":7.616,"active":null,"src":"safetensors","q":null,"stTotal":7.616},"moe":false,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88,"131072":7.52},"mem":{"bf16":{"w":15.23,"t":17.7},"fp8":{"w":8.09,"t":9.9},"q4":{"w":4.62,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.23,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-r1-distill-qwen-7b"},{"id":"deepseek-r1-distill-qwen-14b","name":"DeepSeek-R1-Distill-Qwen-14B","hf":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-R1-Distill-Qwen","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-01-20","updated":"2025-02-24","gated":false,"params":{"total":14.77,"active":null,"src":"safetensors","q":null,"stTotal":14.77},"moe":false,"ctx":131072,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.61,"32768":6.44,"131072":25.77},"mem":{"bf16":{"w":29.54,"t":34.6},"fp8":{"w":15.69,"t":19.4},"q4":{"w":8.95,"t":12}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":29.54,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-r1-distill-qwen-14b"},{"id":"deepseek-r1-distill-qwen-32b","name":"DeepSeek-R1-Distill-Qwen-32B","hf":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-R1-Distill-Qwen","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-01-20","updated":"2025-02-24","gated":false,"params":{"total":32.764,"active":null,"src":"safetensors","q":null,"stTotal":32.764},"moe":false,"ctx":131072,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59,"131072":34.36},"mem":{"bf16":{"w":65.53,"t":74.7},"fp8":{"w":34.81,"t":40.9},"q4":{"w":19.86,"t":24.5}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":65.53,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-r1-distill-qwen-32b"},{"id":"deepseek-r1-0528-qwen3-8b","name":"DeepSeek-R1-0528-Qwen3-8B","hf":"deepseek-ai/DeepSeek-R1-0528-Qwen3-8B","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-R1-Qwen3","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-05-29","updated":"2025-05-29","gated":false,"params":{"total":8.191,"active":null,"src":"safetensors","q":null,"stTotal":8.191},"moe":false,"ctx":131072,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83,"131072":19.33},"mem":{"bf16":{"w":16.38,"t":19.7},"fp8":{"w":8.7,"t":11.3},"q4":{"w":4.97,"t":7.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.38,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-R1-0528-Qwen3-8B","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-R1-0528-Qwen3-8B","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-r1-0528-qwen3-8b"},{"id":"deepseek-r1-zero","name":"DeepSeek-R1-Zero","hf":"deepseek-ai/DeepSeek-R1-Zero","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-R1-Zero","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-01-20","updated":"2025-03-27","gated":false,"params":{"total":671,"active":37,"src":"card","q":"#Total Params 671B, #Activated Params 37B","stTotal":684.49},"moe":true,"ctx":163840,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":1342,"t":1477.3},"fp8":{"w":712.94,"t":785.3},"q4":{"w":406.79,"t":448.6}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":688.59,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-R1-Zero","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-R1-Zero","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-r1-zero/"},{"id":"deepseek-v3-2-speciale","name":"DeepSeek-V3.2-Speciale","hf":"deepseek-ai/DeepSeek-V3.2-Speciale","org":"deepseek-ai","family":"deepseek","series":"DeepSeek-Speciale","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-11-28","updated":"2025-12-01","gated":false,"params":{"total":685.397,"active":null,"src":"safetensors","q":null,"stTotal":685.397},"moe":true,"ctx":163840,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":1370.79,"t":1509},"fp8":{"w":728.23,"t":802.1},"q4":{"w":415.52,"t":458.2}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":689.48,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/DeepSeek-V3.2-Speciale","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/DeepSeek-V3.2-Speciale","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/deepseek-v3-2-speciale/"},{"id":"deepseek-vl2","name":"deepseek-vl2","hf":"deepseek-ai/deepseek-vl2","org":"deepseek-ai","family":"deepseek","series":"deepseek-vl2","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-12-13","updated":"2024-12-18","gated":false,"params":{"total":27.48,"active":null,"src":"safetensors","q":null,"stTotal":27.48},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":54.96,"t":61},"fp8":{"w":29.2,"t":32.6},"q4":{"w":16.66,"t":18.8}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":54.96,"native":"BF16","license":{"id":"deepseek","name":"deepseek","link":"https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/deepseek-vl2","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/deepseek-vl2","u":"https://huggingface.co/deepseek-ai/deepseek-vl2"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/deepseek-vl2/blob/main/config.json"},{"t":"License","u":"https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-vl2"},{"id":"deepseek-vl2-small","name":"deepseek-vl2-small","hf":"deepseek-ai/deepseek-vl2-small","org":"deepseek-ai","family":"deepseek","series":"deepseek-vl2-small","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-12-13","updated":"2024-12-18","gated":false,"params":{"total":16.148,"active":2.8,"src":"safetensors","q":"DeepSeek-VL2-Tiny, DeepSeek-VL2-Small and DeepSeek-VL2, with 1.0B, 2.8B and 4.5B activated parameters respectively.","stTotal":16.148},"moe":true,"ctx":4096,"arch":{"L":27,"attn":27,"slide":0,"win":null,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.81},"mem":{"bf16":{"w":32.3,"t":37.8},"fp8":{"w":17.16,"t":21.2},"q4":{"w":9.79,"t":13.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":32.3,"native":"BF16","license":{"id":"deepseek","name":"deepseek","link":"https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/deepseek-vl2-small","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/deepseek-vl2-small","u":"https://huggingface.co/deepseek-ai/deepseek-vl2-small"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/deepseek-vl2-small/blob/main/config.json"},{"t":"License","u":"https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-vl2-small"},{"id":"deepseek-vl2-tiny","name":"deepseek-vl2-tiny","hf":"deepseek-ai/deepseek-vl2-tiny","org":"deepseek-ai","family":"deepseek","series":"deepseek-vl2-tiny","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-12-13","updated":"2024-12-18","gated":false,"params":{"total":3.371,"active":1,"src":"safetensors","q":"DeepSeek-VL2-Tiny, DeepSeek-VL2-Small and DeepSeek-VL2, with 1.0B, 2.8B and 4.5B activated parameters respectively.","stTotal":3.371},"moe":true,"ctx":4096,"arch":{"L":12,"attn":12,"slide":0,"win":null,"kvElems":2560,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.5},"mem":{"bf16":{"w":6.74,"t":8.4},"fp8":{"w":3.58,"t":4.9},"q4":{"w":2.04,"t":3.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.74,"native":"BF16","license":{"id":"deepseek","name":"deepseek","link":"https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"deepseek-ai/deepseek-vl2-tiny","kind":"main"}],"sources":[{"t":"Hugging Face · deepseek-ai/deepseek-vl2-tiny","u":"https://huggingface.co/deepseek-ai/deepseek-vl2-tiny"},{"t":"config.json","u":"https://huggingface.co/deepseek-ai/deepseek-vl2-tiny/blob/main/config.json"},{"t":"License","u":"https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL"}],"page":"https://aimap.page/en/models/compute/open-models/family/deepseek/#m-deepseek-vl2-tiny"},{"id":"dots-llm1-base","name":"dots.llm1.base","hf":"rednote-hilab/dots.llm1.base","org":"rednote-hilab","family":"dots","series":"dots.llm1.base","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-10-06","updated":"2026-10-07","gated":false,"params":{"total":142,"active":14,"src":"card","q":"activates 14B parameters out of a total of 142B parameters","stTotal":1.544},"moe":true,"ctx":32768,"arch":{"L":62,"attn":62,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":8.32,"32768":33.29},"mem":{"bf16":{"w":284,"t":321.2},"fp8":{"w":150.88,"t":174.8},"q4":{"w":86.09,"t":103.5}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"h200","mac":"mac256"}},"disk":6.17,"native":"F32","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/rednote-hilab/dots.llm1.base/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"rednote-hilab/dots.llm1.base","kind":"Base"}],"sources":[{"t":"Hugging Face · rednote-hilab/dots.llm1.base","u":"https://huggingface.co/rednote-hilab/dots.llm1.base"},{"t":"config.json","u":"https://huggingface.co/rednote-hilab/dots.llm1.base/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/rednote-hilab/dots.llm1.base/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/dots-llm1-base/"},{"id":"ernie-4-5-0-3b-pt","name":"ERNIE-4.5-0.3B-PT","hf":"baidu/ERNIE-4.5-0.3B-PT","org":"baidu","family":"ernie","series":"ERNIE-4.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-28","updated":"2025-08-29","gated":false,"params":{"total":0.361,"active":null,"src":"safetensors","q":null,"stTotal":0.361},"moe":false,"ctx":131072,"arch":{"L":18,"attn":18,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.15,"32768":0.6,"131072":2.42},"mem":{"bf16":{"w":0.72,"t":1.4},"fp8":{"w":0.38,"t":1.1},"q4":{"w":0.22,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.72,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"baidu/ERNIE-4.5-0.3B-PT","kind":"Base"},{"id":"baidu/ERNIE-4.5-0.3B-Base-PT","kind":"Base"}],"sources":[{"t":"Hugging Face · baidu/ERNIE-4.5-0.3B-PT","u":"https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT"},{"t":"config.json","u":"https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/ernie/#m-ernie-4-5-0-3b-pt"},{"id":"ernie-4-5-21b-a3b-pt","name":"ERNIE-4.5-21B-A3B-PT","hf":"baidu/ERNIE-4.5-21B-A3B-PT","org":"baidu","family":"ernie","series":"ERNIE-4.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-28","updated":"2025-11-26","gated":false,"params":{"total":21.949,"active":3,"src":"safetensors","q":null,"stTotal":21.949},"moe":true,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88,"131072":7.52},"mem":{"bf16":{"w":43.9,"t":49.3},"fp8":{"w":23.32,"t":26.6},"q4":{"w":13.31,"t":15.6}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":43.91,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"baidu/ERNIE-4.5-21B-A3B-PT","kind":"Base"}],"sources":[{"t":"Hugging Face · baidu/ERNIE-4.5-21B-A3B-PT","u":"https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT"},{"t":"config.json","u":"https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/ernie/#m-ernie-4-5-21b-a3b-pt"},{"id":"ernie-4-5-300b-a47b-pt","name":"ERNIE-4.5-300B-A47B-PT","hf":"baidu/ERNIE-4.5-300B-A47B-PT","org":"baidu","family":"ernie","series":"ERNIE-4.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-28","updated":"2025-11-26","gated":false,"params":{"total":300.474,"active":47,"src":"safetensors","q":null,"stTotal":300.474},"moe":true,"ctx":131072,"arch":{"L":54,"attn":54,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.81,"32768":7.25,"131072":28.99},"mem":{"bf16":{"w":600.95,"t":663.4},"fp8":{"w":319.25,"t":353.5},"q4":{"w":182.16,"t":202.7}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":601,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baidu/ERNIE-4.5-300B-A47B-PT/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"baidu/ERNIE-4.5-300B-A47B-PT","kind":"Base"},{"id":"baidu/ERNIE-4.5-300B-A47B-Base-PT","kind":"Base"}],"sources":[{"t":"Hugging Face · baidu/ERNIE-4.5-300B-A47B-PT","u":"https://huggingface.co/baidu/ERNIE-4.5-300B-A47B-PT"},{"t":"config.json","u":"https://huggingface.co/baidu/ERNIE-4.5-300B-A47B-PT/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/baidu/ERNIE-4.5-300B-A47B-PT/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/ernie-4-5-300b-a47b-pt/"},{"id":"ernie-4-5-300b-a47b-paddle","name":"ERNIE-4.5-300B-A47B-Paddle","hf":"baidu/ERNIE-4.5-300B-A47B-Paddle","org":"baidu","family":"ernie","series":"ERNIE-4.5-Paddle","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-28","updated":"2025-09-09","gated":false,"params":{"total":300.474,"active":47,"src":"safetensors","q":null,"stTotal":300.474},"moe":true,"ctx":131072,"arch":{"L":54,"attn":54,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.81,"32768":7.25,"131072":28.99},"mem":{"bf16":{"w":600.95,"t":663.4},"fp8":{"w":319.25,"t":353.5},"q4":{"w":182.16,"t":202.7}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":601.02,"native":"U16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baidu/ERNIE-4.5-300B-A47B-Paddle/blob/main/LICENSE","cls":"open"},"runtimes":[],"variants":[{"id":"baidu/ERNIE-4.5-300B-A47B-Paddle","kind":"main"},{"id":"baidu/ERNIE-4.5-300B-A47B-Base-Paddle","kind":"Base"},{"id":"baidu/ERNIE-4.5-300B-A47B-FP8-Paddle","kind":"FP8"}],"sources":[{"t":"Hugging Face · baidu/ERNIE-4.5-300B-A47B-Paddle","u":"https://huggingface.co/baidu/ERNIE-4.5-300B-A47B-Paddle"},{"t":"config.json","u":"https://huggingface.co/baidu/ERNIE-4.5-300B-A47B-Paddle/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/baidu/ERNIE-4.5-300B-A47B-Paddle/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/ernie-4-5-300b-a47b-paddle/"},{"id":"ernie-4-5-21b-a3b-thinking","name":"ERNIE-4.5-21B-A3B-Thinking","hf":"baidu/ERNIE-4.5-21B-A3B-Thinking","org":"baidu","family":"ernie","series":"ERNIE-4.5-Thinking","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-09-08","updated":"2025-11-26","gated":false,"params":{"total":21.825,"active":3,"src":"safetensors","q":null,"stTotal":21.825},"moe":true,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88,"131072":7.52},"mem":{"bf16":{"w":43.65,"t":49},"fp8":{"w":23.19,"t":26.5},"q4":{"w":13.23,"t":15.5}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":43.66,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"baidu/ERNIE-4.5-21B-A3B-Thinking","kind":"main"}],"sources":[{"t":"Hugging Face · baidu/ERNIE-4.5-21B-A3B-Thinking","u":"https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking"},{"t":"config.json","u":"https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/ernie/#m-ernie-4-5-21b-a3b-thinking"},{"id":"ernie-4-5-vl-28b-a3b-pt","name":"ERNIE-4.5-VL-28B-A3B-PT","hf":"baidu/ERNIE-4.5-VL-28B-A3B-PT","org":"baidu","family":"ernie","series":"ERNIE-4.5-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-06-28","updated":"2026-04-20","gated":false,"params":{"total":29.399,"active":3,"src":"safetensors","q":null,"stTotal":29.399},"moe":true,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88,"131072":7.52},"mem":{"bf16":{"w":58.8,"t":65.6},"fp8":{"w":31.24,"t":35.3},"q4":{"w":17.82,"t":20.6}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":58.82,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baidu/ERNIE-4.5-VL-28B-A3B-PT/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"baidu/ERNIE-4.5-VL-28B-A3B-PT","kind":"Base"}],"sources":[{"t":"Hugging Face · baidu/ERNIE-4.5-VL-28B-A3B-PT","u":"https://huggingface.co/baidu/ERNIE-4.5-VL-28B-A3B-PT"},{"t":"config.json","u":"https://huggingface.co/baidu/ERNIE-4.5-VL-28B-A3B-PT/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/baidu/ERNIE-4.5-VL-28B-A3B-PT/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/ernie/#m-ernie-4-5-vl-28b-a3b-pt"},{"id":"ernie-4-5-vl-424b-a47b-pt","name":"ERNIE-4.5-VL-424B-A47B-PT","hf":"baidu/ERNIE-4.5-VL-424B-A47B-PT","org":"baidu","family":"ernie","series":"ERNIE-4.5-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-06-28","updated":"2026-01-16","gated":false,"params":{"total":423.526,"active":47,"src":"safetensors","q":null,"stTotal":423.526},"moe":true,"ctx":131072,"arch":{"L":54,"attn":54,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.81,"32768":7.25,"131072":28.99},"mem":{"bf16":{"w":847.05,"t":934.1},"fp8":{"w":450,"t":497.3},"q4":{"w":256.76,"t":284.7}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":847.16,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-PT/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"baidu/ERNIE-4.5-VL-424B-A47B-PT","kind":"Base"},{"id":"baidu/ERNIE-4.5-VL-424B-A47B-Base-PT","kind":"Base"}],"sources":[{"t":"Hugging Face · baidu/ERNIE-4.5-VL-424B-A47B-PT","u":"https://huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-PT"},{"t":"config.json","u":"https://huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-PT/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-PT/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/ernie-4-5-vl-424b-a47b-pt/"},{"id":"ernie-4-5-vl-424b-a47b-paddle","name":"ERNIE-4.5-VL-424B-A47B-Paddle","hf":"baidu/ERNIE-4.5-VL-424B-A47B-Paddle","org":"baidu","family":"ernie","series":"ERNIE-4.5-VL-Paddle","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-06-28","updated":"2025-08-20","gated":false,"params":{"total":423.526,"active":47,"src":"safetensors","q":null,"stTotal":423.526},"moe":true,"ctx":131072,"arch":{"L":54,"attn":54,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.81,"32768":7.25,"131072":28.99},"mem":{"bf16":{"w":847.05,"t":934.1},"fp8":{"w":450,"t":497.3},"q4":{"w":256.76,"t":284.7}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":847.16,"native":"U16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-Paddle/blob/main/LICENSE","cls":"open"},"runtimes":[],"variants":[{"id":"baidu/ERNIE-4.5-VL-424B-A47B-Paddle","kind":"main"}],"sources":[{"t":"Hugging Face · baidu/ERNIE-4.5-VL-424B-A47B-Paddle","u":"https://huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-Paddle"},{"t":"config.json","u":"https://huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-Paddle/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-Paddle/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/ernie-4-5-vl-424b-a47b-paddle/"},{"id":"ernie-4-5-vl-28b-a3b-thinking","name":"ERNIE-4.5-VL-28B-A3B-Thinking","hf":"baidu/ERNIE-4.5-VL-28B-A3B-Thinking","org":"baidu","family":"ernie","series":"ERNIE-4.5-VL-Thinking","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-11-07","updated":"2026-03-06","gated":false,"params":{"total":29.664,"active":3,"src":"safetensors","q":null,"stTotal":29.664},"moe":true,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88,"131072":7.52},"mem":{"bf16":{"w":59.33,"t":66.2},"fp8":{"w":31.52,"t":35.6},"q4":{"w":17.98,"t":20.8}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":59.35,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"baidu/ERNIE-4.5-VL-28B-A3B-Thinking","kind":"main"}],"sources":[{"t":"Hugging Face · baidu/ERNIE-4.5-VL-28B-A3B-Thinking","u":"https://huggingface.co/baidu/ERNIE-4.5-VL-28B-A3B-Thinking"},{"t":"config.json","u":"https://huggingface.co/baidu/ERNIE-4.5-VL-28B-A3B-Thinking/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ernie/#m-ernie-4-5-vl-28b-a3b-thinking"},{"id":"ernie-image","name":"ERNIE-Image","hf":"baidu/ERNIE-Image","org":"baidu","family":"ernie","series":"ERNIE-Image","task":"image","pipeline":"text-to-image","tags":[],"released":"2026-04-07","updated":"2026-04-17","gated":false,"params":{"total":8.033,"active":null,"src":"safetensors","q":null,"stTotal":8.033},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":16.07,"t":18.2},"fp8":{"w":8.54,"t":9.9},"q4":{"w":4.87,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":31.6,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baidu/ERNIE-Image/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"baidu/ERNIE-Image","kind":"main"}],"sources":[{"t":"Hugging Face · baidu/ERNIE-Image","u":"https://huggingface.co/baidu/ERNIE-Image"},{"t":"License","u":"https://huggingface.co/baidu/ERNIE-Image/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/ernie/#m-ernie-image"},{"id":"ernie-image-turbo","name":"ERNIE-Image-Turbo","hf":"baidu/ERNIE-Image-Turbo","org":"baidu","family":"ernie","series":"ERNIE-Image-Turbo","task":"image","pipeline":"text-to-image","tags":[],"released":"2026-04-02","updated":"2026-04-17","gated":false,"params":{"total":8.033,"active":null,"src":"safetensors","q":null,"stTotal":8.033},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":16.07,"t":18.2},"fp8":{"w":8.54,"t":9.9},"q4":{"w":4.87,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":31.6,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/baidu/ERNIE-Image-Turbo/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"baidu/ERNIE-Image-Turbo","kind":"main"}],"sources":[{"t":"Hugging Face · baidu/ERNIE-Image-Turbo","u":"https://huggingface.co/baidu/ERNIE-Image-Turbo"},{"t":"License","u":"https://huggingface.co/baidu/ERNIE-Image-Turbo/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/ernie/#m-ernie-image-turbo"},{"id":"flux-1-canny-dev","name":"FLUX.1-Canny-dev","hf":"black-forest-labs/FLUX.1-Canny-dev","org":"black-forest-labs","family":"flux","series":"FLUX.1-Canny-dev","task":"image","pipeline":"text-to-image","tags":[],"released":"2024-11-20","updated":"2025-06-27","gated":true,"params":{"total":11.902,"active":null,"src":"safetensors","q":null,"stTotal":11.902},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":23.8,"t":26.7},"fp8":{"w":12.65,"t":14.4},"q4":{"w":7.22,"t":8.4}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24.14,"native":"BF16","license":{"id":"flux-1-dev-non-commercial-license","name":"flux-1-dev-non-commercial-license","link":"https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev/blob/main/LICENSE.md","cls":"nc"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.1-Canny-dev","kind":"main"},{"id":"black-forest-labs/FLUX.1-Canny-dev-onnx","kind":"ONNX"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.1-Canny-dev","u":"https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev"},{"t":"License","u":"https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-1-canny-dev"},{"id":"flux-1-depth-dev","name":"FLUX.1-Depth-dev","hf":"black-forest-labs/FLUX.1-Depth-dev","org":"black-forest-labs","family":"flux","series":"FLUX.1-Depth-dev","task":"image","pipeline":"text-to-image","tags":[],"released":"2024-11-20","updated":"2025-06-27","gated":true,"params":{"total":11.902,"active":null,"src":"safetensors","q":null,"stTotal":11.902},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":23.8,"t":26.7},"fp8":{"w":12.65,"t":14.4},"q4":{"w":7.22,"t":8.4}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24.14,"native":"BF16","license":{"id":"flux-1-dev-non-commercial-license","name":"flux-1-dev-non-commercial-license","link":"https://huggingface.co/black-forest-labs/FLUX.1-Depth-dev/blob/main/LICENSE.md","cls":"nc"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.1-Depth-dev","kind":"main"},{"id":"black-forest-labs/FLUX.1-Depth-dev-onnx","kind":"ONNX"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.1-Depth-dev","u":"https://huggingface.co/black-forest-labs/FLUX.1-Depth-dev"},{"t":"License","u":"https://huggingface.co/black-forest-labs/FLUX.1-Depth-dev/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-1-depth-dev"},{"id":"flux-1-fill-dev","name":"FLUX.1-Fill-dev","hf":"black-forest-labs/FLUX.1-Fill-dev","org":"black-forest-labs","family":"flux","series":"FLUX.1-Fill-dev","task":"image","pipeline":null,"tags":[],"released":"2024-11-20","updated":"2025-06-27","gated":true,"params":{"total":11.902,"active":null,"src":"safetensors","q":null,"stTotal":11.902},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":23.8,"t":26.7},"fp8":{"w":12.65,"t":14.4},"q4":{"w":7.22,"t":8.4}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24.14,"native":"BF16","license":{"id":"flux-1-dev-non-commercial-license","name":"flux-1-dev-non-commercial-license","link":"https://huggingface.co/black-forest-labs/FLUX.1-Fill-dev/blob/main/LICENSE.md","cls":"nc"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.1-Fill-dev","kind":"main"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.1-Fill-dev","u":"https://huggingface.co/black-forest-labs/FLUX.1-Fill-dev"},{"t":"License","u":"https://huggingface.co/black-forest-labs/FLUX.1-Fill-dev/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-1-fill-dev"},{"id":"flux-1-kontext-dev","name":"FLUX.1-Kontext-dev","hf":"black-forest-labs/FLUX.1-Kontext-dev","org":"black-forest-labs","family":"flux","series":"FLUX.1-Kontext-dev","task":"image","pipeline":"image-to-image","tags":[],"released":"2025-05-28","updated":"2026-01-01","gated":true,"params":{"total":11.901,"active":null,"src":"safetensors","q":null,"stTotal":11.901},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":23.8,"t":26.7},"fp8":{"w":12.64,"t":14.4},"q4":{"w":7.21,"t":8.4}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24.14,"native":"BF16","license":{"id":"flux-1-dev-non-commercial-license","name":"flux-1-dev-non-commercial-license","link":"https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev/blob/main/LICENSE.md","cls":"nc"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.1-Kontext-dev","kind":"main"},{"id":"black-forest-labs/FLUX.1-Kontext-dev-NVFP4","kind":"NVFP4"},{"id":"black-forest-labs/FLUX.1-Kontext-dev-onnx","kind":"ONNX"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.1-Kontext-dev","u":"https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev"},{"t":"License","u":"https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-1-kontext-dev"},{"id":"flux-1-krea-dev","name":"FLUX.1-Krea-dev","hf":"black-forest-labs/FLUX.1-Krea-dev","org":"black-forest-labs","family":"flux","series":"FLUX.1-Krea-dev","task":"image","pipeline":"text-to-image","tags":[],"released":"2025-07-07","updated":"2025-07-31","gated":true,"params":{"total":11.901,"active":null,"src":"safetensors","q":null,"stTotal":11.901},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":23.8,"t":26.7},"fp8":{"w":12.64,"t":14.4},"q4":{"w":7.21,"t":8.4}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24.14,"native":"BF16","license":{"id":"flux-1-dev-non-commercial-license","name":"flux-1-dev-non-commercial-license","link":"https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev/blob/main/LICENSE.md","cls":"nc"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.1-Krea-dev","kind":"main"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.1-Krea-dev","u":"https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev"},{"t":"License","u":"https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-1-krea-dev"},{"id":"flux-1-redux-dev","name":"FLUX.1-Redux-dev","hf":"black-forest-labs/FLUX.1-Redux-dev","org":"black-forest-labs","family":"flux","series":"FLUX.1-Redux-dev","task":"image","pipeline":null,"tags":[],"released":"2024-11-20","updated":"2025-06-27","gated":true,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":0.13,"native":null,"license":{"id":"flux-1-dev-non-commercial-license","name":"flux-1-dev-non-commercial-license","link":"https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev/blob/main/LICENSE.md","cls":"nc"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.1-Redux-dev","kind":"main"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.1-Redux-dev","u":"https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev"},{"t":"License","u":"https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-1-redux-dev"},{"id":"flux-1-dev","name":"FLUX.1-dev","hf":"black-forest-labs/FLUX.1-dev","org":"black-forest-labs","family":"flux","series":"FLUX.1-dev","task":"image","pipeline":"text-to-image","tags":[],"released":"2024-07-31","updated":"2025-06-27","gated":true,"params":{"total":11.901,"active":null,"src":"safetensors","q":null,"stTotal":11.901},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":23.8,"t":26.7},"fp8":{"w":12.64,"t":14.4},"q4":{"w":7.21,"t":8.4}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24.14,"native":"BF16","license":{"id":"flux-1-dev-non-commercial-license","name":"flux-1-dev-non-commercial-license","link":"https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md","cls":"nc"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.1-dev","kind":"main"},{"id":"black-forest-labs/FLUX.1-dev-FP8","kind":"FP8"},{"id":"black-forest-labs/FLUX.1-dev-onnx","kind":"ONNX"},{"id":"black-forest-labs/FLUX.1-dev-NVFP4","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.1-dev","u":"https://huggingface.co/black-forest-labs/FLUX.1-dev"},{"t":"License","u":"https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-1-dev"},{"id":"flux-1-schnell","name":"FLUX.1-schnell","hf":"black-forest-labs/FLUX.1-schnell","org":"black-forest-labs","family":"flux","series":"FLUX.1-schnell","task":"image","pipeline":"text-to-image","tags":[],"released":"2024-07-31","updated":"2024-08-16","gated":true,"params":{"total":11.891,"active":null,"src":"safetensors","q":null,"stTotal":11.891},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":23.78,"t":26.7},"fp8":{"w":12.63,"t":14.4},"q4":{"w":7.21,"t":8.4}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24.12,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.1-schnell","kind":"main"},{"id":"black-forest-labs/FLUX.1-schnell-onnx","kind":"ONNX"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.1-schnell","u":"https://huggingface.co/black-forest-labs/FLUX.1-schnell"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-1-schnell"},{"id":"flux-2-dev","name":"FLUX.2-dev","hf":"black-forest-labs/FLUX.2-dev","org":"black-forest-labs","family":"flux","series":"FLUX.2-dev","task":"image","pipeline":"image-to-image","tags":[],"released":"2025-11-22","updated":"2026-02-17","gated":true,"params":{"total":32.223,"active":null,"src":"safetensors","q":null,"stTotal":32.223},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":64.45,"t":71.4},"fp8":{"w":34.24,"t":38.2},"q4":{"w":19.54,"t":22}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":64.78,"native":"BF16","license":{"id":"flux-non-commercial-license","name":"flux-non-commercial-license","link":"https://huggingface.co/black-forest-labs/FLUX.2-dev/blob/main/LICENSE.md","cls":"nc"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.2-dev","kind":"main"},{"id":"black-forest-labs/FLUX.2-dev-NVFP4","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.2-dev","u":"https://huggingface.co/black-forest-labs/FLUX.2-dev"},{"t":"License","u":"https://huggingface.co/black-forest-labs/FLUX.2-dev/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-2-dev"},{"id":"flux-2-klein-4b","name":"FLUX.2-klein-4B","hf":"black-forest-labs/FLUX.2-klein-4B","org":"black-forest-labs","family":"flux","series":"FLUX.2-klein","task":"image","pipeline":"image-to-image","tags":[],"released":"2026-01-14","updated":"2026-02-24","gated":false,"params":{"total":3.876,"active":null,"src":"safetensors","q":null,"stTotal":3.876},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":7.75,"t":9},"fp8":{"w":4.12,"t":5},"q4":{"w":2.35,"t":3.1}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.75,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/black-forest-labs/FLUX.2-klein-4B/blob/main/LICENSE.md","cls":"open"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.2-klein-base-4B","kind":"Base"},{"id":"black-forest-labs/FLUX.2-klein-4B","kind":"main"},{"id":"black-forest-labs/FLUX.2-klein-4b-fp8","kind":"FP8"},{"id":"black-forest-labs/FLUX.2-klein-base-4b-fp8","kind":"Base/FP8"},{"id":"black-forest-labs/FLUX.2-klein-4b-nvfp4","kind":"NVFP4"},{"id":"black-forest-labs/FLUX.2-klein-base-4b-nvfp4","kind":"Base/NVFP4"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.2-klein-4B","u":"https://huggingface.co/black-forest-labs/FLUX.2-klein-4B"},{"t":"License","u":"https://huggingface.co/black-forest-labs/FLUX.2-klein-4B/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-2-klein-4b"},{"id":"flux-2-klein-9b","name":"FLUX.2-klein-9B","hf":"black-forest-labs/FLUX.2-klein-9B","org":"black-forest-labs","family":"flux","series":"FLUX.2-klein","task":"image","pipeline":"image-to-image","tags":[],"released":"2026-01-14","updated":"2026-02-24","gated":true,"params":{"total":9.079,"active":null,"src":"safetensors","q":null,"stTotal":9.079},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":18.16,"t":20.5},"fp8":{"w":9.65,"t":11.1},"q4":{"w":5.5,"t":6.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":18.16,"native":"BF16","license":{"id":"flux-non-commercial-license","name":"flux-non-commercial-license","link":"https://huggingface.co/black-forest-labs/FLUX.2-klein-9B/blob/main/LICENSE.md","cls":"nc"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.2-klein-9B","kind":"main"},{"id":"black-forest-labs/FLUX.2-klein-base-9B","kind":"Base"},{"id":"black-forest-labs/FLUX.2-klein-9b-fp8","kind":"FP8"},{"id":"black-forest-labs/FLUX.2-klein-base-9b-fp8","kind":"Base/FP8"},{"id":"black-forest-labs/FLUX.2-klein-9b-nvfp4","kind":"NVFP4"},{"id":"black-forest-labs/FLUX.2-klein-base-9b-nvfp4","kind":"Base/NVFP4"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.2-klein-9B","u":"https://huggingface.co/black-forest-labs/FLUX.2-klein-9B"},{"t":"License","u":"https://huggingface.co/black-forest-labs/FLUX.2-klein-9B/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-2-klein-9b"},{"id":"flux-2-klein-9b-kv","name":"FLUX.2-klein-9b-kv","hf":"black-forest-labs/FLUX.2-klein-9b-kv","org":"black-forest-labs","family":"flux","series":"FLUX.2-klein-kv","task":"image","pipeline":"image-to-image","tags":[],"released":"2026-03-09","updated":"2026-03-12","gated":true,"params":{"total":9.079,"active":null,"src":"safetensors","q":null,"stTotal":9.079},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":18.16,"t":20.5},"fp8":{"w":9.65,"t":11.1},"q4":{"w":5.5,"t":6.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":18.16,"native":"BF16","license":{"id":"flux-non-commercial-license","name":"flux-non-commercial-license","link":"https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-kv/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"black-forest-labs/FLUX.2-klein-9b-kv-fp8","kind":"FP8"},{"id":"black-forest-labs/FLUX.2-klein-9b-kv","kind":"main"}],"sources":[{"t":"Hugging Face · black-forest-labs/FLUX.2-klein-9b-kv","u":"https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-kv"},{"t":"License","u":"https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-kv/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/flux/#m-flux-2-klein-9b-kv"},{"id":"flux-3-image-klein","name":"flux-3-image-klein","hf":"black-forest-labs/flux-3-image-klein","org":"black-forest-labs","family":"flux","series":"flux-3-image-klein","task":"image","pipeline":"image-to-image","tags":[],"released":"2026-10-13","updated":"2026-10-16","gated":true,"params":{"total":5.549,"active":null,"src":"safetensors","q":null,"stTotal":5.549},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":11.1,"t":12.7},"fp8":{"w":5.9,"t":7},"q4":{"w":3.36,"t":4.2}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":11.43,"native":"BF16","license":{"id":"flux-kommunity-license","name":"flux-kommunity-license","link":"https://huggingface.co/black-forest-labs/flux-3-image-klein/blob/main/LICENSE.md","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"black-forest-labs/flux-3-image-klein-base","kind":"Base"},{"id":"black-forest-labs/flux-3-image-klein","kind":"main"}],"sources":[{"t":"Hugging Face · black-forest-labs/flux-3-image-klein","u":"https://huggingface.co/black-forest-labs/flux-3-image-klein"},{"t":"License","u":"https://huggingface.co/black-forest-labs/flux-3-image-klein/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/flux-3-image-klein/"},{"id":"flux-3-image-klein-pup","name":"flux-3-image-klein-pup","hf":"black-forest-labs/flux-3-image-klein-pup","org":"black-forest-labs","family":"flux","series":"flux-3-image-klein-pup","task":"image","pipeline":"image-text-to-text","tags":[],"released":"2026-10-14","updated":"2026-10-15","gated":false,"params":{"total":9.41,"active":null,"src":"safetensors","q":null,"stTotal":9.41},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":18.82,"t":21.2},"fp8":{"w":10,"t":11.5},"q4":{"w":5.7,"t":6.8}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":18.82,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"black-forest-labs/flux-3-image-klein-pup","kind":"main"}],"sources":[{"t":"Hugging Face · black-forest-labs/flux-3-image-klein-pup","u":"https://huggingface.co/black-forest-labs/flux-3-image-klein-pup"},{"t":"config.json","u":"https://huggingface.co/black-forest-labs/flux-3-image-klein-pup/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/flux-3-image-klein-pup/"},{"id":"cosyvoice2-0-5b","name":"CosyVoice2-0.5B","hf":"FunAudioLLM/CosyVoice2-0.5B","org":"FunAudioLLM","family":"funaudio","series":"CosyVoice2","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2025-07-29","updated":"2026-05-31","gated":false,"params":{"total":0.5,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1,"t":1.6},"fp8":{"w":0.53,"t":1.1},"q4":{"w":0.3,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.99,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"FunAudioLLM/CosyVoice2-0.5B","kind":"main"}],"sources":[{"t":"Hugging Face · FunAudioLLM/CosyVoice2-0.5B","u":"https://huggingface.co/FunAudioLLM/CosyVoice2-0.5B"}],"page":"https://aimap.page/en/models/compute/open-models/family/funaudio/#m-cosyvoice2-0-5b"},{"id":"fun-asr-mlt-nano-2512","name":"Fun-ASR-MLT-Nano-2512","hf":"FunAudioLLM/Fun-ASR-MLT-Nano-2512","org":"FunAudioLLM","family":"funaudio","series":"Fun-ASR-MLT-Nano","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-12-15","updated":"2026-08-05","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":1.97,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"}],"variants":[{"id":"FunAudioLLM/Fun-ASR-MLT-Nano-2512","kind":"main"}],"sources":[{"t":"Hugging Face · FunAudioLLM/Fun-ASR-MLT-Nano-2512","u":"https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512"}],"page":"https://aimap.page/en/models/compute/open-models/family/funaudio/#m-fun-asr-mlt-nano-2512"},{"id":"fun-asr-nano-2512-hf","name":"Fun-ASR-Nano-2512-hf","hf":"FunAudioLLM/Fun-ASR-Nano-2512-hf","org":"FunAudioLLM","family":"funaudio","series":"Fun-ASR-Nano","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-05-24","updated":"2026-09-10","gated":false,"params":{"total":0.83,"active":null,"src":"safetensors","q":null,"stTotal":0.83},"moe":false,"ctx":40960,"arch":null,"kv":null,"mem":{"bf16":{"w":1.66,"t":2.3},"fp8":{"w":0.88,"t":1.5},"q4":{"w":0.5,"t":1.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.66,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"FunAudioLLM/Fun-ASR-Nano-2512-hf","kind":"HF-transformers"},{"id":"FunAudioLLM/Fun-ASR-Nano-2512-GGUF","kind":"GGUF"},{"id":"FunAudioLLM/Fun-ASR-Nano-2512","kind":"main"}],"sources":[{"t":"Hugging Face · FunAudioLLM/Fun-ASR-Nano-2512-hf","u":"https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512-hf"},{"t":"config.json","u":"https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512-hf/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/funaudio/#m-fun-asr-nano-2512-hf"},{"id":"fun-cosyvoice3-0-5b-2512","name":"Fun-CosyVoice3-0.5B-2512","hf":"FunAudioLLM/Fun-CosyVoice3-0.5B-2512","org":"FunAudioLLM","family":"funaudio","series":"Fun-CosyVoice3","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2025-12-11","updated":"2026-02-03","gated":false,"params":{"total":0.5,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1,"t":1.6},"fp8":{"w":0.53,"t":1.1},"q4":{"w":0.3,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.99,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"FunAudioLLM/Fun-CosyVoice3-0.5B-2512","kind":"main"}],"sources":[{"t":"Hugging Face · FunAudioLLM/Fun-CosyVoice3-0.5B-2512","u":"https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512"}],"page":"https://aimap.page/en/models/compute/open-models/family/funaudio/#m-fun-cosyvoice3-0-5b-2512"},{"id":"sensevoicesmall","name":"SenseVoiceSmall","hf":"FunAudioLLM/SenseVoiceSmall","org":"FunAudioLLM","family":"funaudio","series":"SenseVoiceSmall","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2024-07-03","updated":"2026-06-20","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":0.94,"native":null,"license":{"id":"model-license","name":"model-license","link":"https://github.com/modelscope/FunASR/blob/main/MODEL_LICENSE","cls":"custom"},"runtimes":[{"id":"llamacpp","via":"card"}],"variants":[{"id":"FunAudioLLM/SenseVoiceSmall","kind":"main"},{"id":"FunAudioLLM/SenseVoiceSmall-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · FunAudioLLM/SenseVoiceSmall","u":"https://huggingface.co/FunAudioLLM/SenseVoiceSmall"},{"t":"License","u":"https://github.com/modelscope/FunASR/blob/main/MODEL_LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/funaudio/#m-sensevoicesmall"},{"id":"diffusiongemma-26b-a4b-it","name":"diffusiongemma-26B-A4B-it","hf":"google/diffusiongemma-26B-A4B-it","org":"google","family":"gemma","series":"diffusiongemma","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-06-09","updated":"2026-07-15","gated":false,"params":{"total":25.824,"active":4,"src":"safetensors","q":null,"stTotal":25.824},"moe":true,"ctx":262144,"arch":{"L":30,"attn":5,"slide":25,"win":1024,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.55,"32768":1.55,"131072":5.58},"mem":{"bf16":{"w":51.65,"t":57.9},"fp8":{"w":27.44,"t":31.2},"q4":{"w":15.66,"t":18.3}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":51.65,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://ai.google.dev/gemma/docs/gemma_4_license","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/diffusiongemma-26B-A4B-it","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/diffusiongemma-26B-A4B-it","u":"https://huggingface.co/google/diffusiongemma-26B-A4B-it"},{"t":"config.json","u":"https://huggingface.co/google/diffusiongemma-26B-A4B-it/blob/main/config.json"},{"t":"License","u":"https://ai.google.dev/gemma/docs/gemma_4_license"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-diffusiongemma-26b-a4b-it"},{"id":"embeddinggemma-300m","name":"embeddinggemma-300m","hf":"google/embeddinggemma-300m","org":"google","family":"gemma","series":"embeddinggemma","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2025-07-17","updated":"2025-09-25","gated":true,"params":{"total":0.303,"active":null,"src":"safetensors","q":null,"stTotal":0.303},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.61,"t":1.2},"fp8":{"w":0.32,"t":0.9},"q4":{"w":0.18,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.21,"native":"F32","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"embeddinggemma:300m","url":"https://ollama.com/library/embeddinggemma"}],"variants":[{"id":"google/embeddinggemma-300m","kind":"main"}],"sources":[{"t":"Hugging Face · google/embeddinggemma-300m","u":"https://huggingface.co/google/embeddinggemma-300m"},{"t":"Ollama library · embeddinggemma","u":"https://ollama.com/library/embeddinggemma"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-embeddinggemma-300m"},{"id":"embeddinggemma-2","name":"embeddinggemma-2","hf":"google/embeddinggemma-2","org":"google","family":"gemma","series":"embeddinggemma-2","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-09-14","updated":"2026-10-06","gated":false,"params":{"total":0.744,"active":null,"src":"safetensors","q":null,"stTotal":0.744},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":1.49,"t":2.1},"fp8":{"w":0.79,"t":1.4},"q4":{"w":0.45,"t":1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.49,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"embeddinggemma-2","url":"https://ollama.com/library/embeddinggemma-2"}],"variants":[{"id":"google/embeddinggemma-2","kind":"main"}],"sources":[{"t":"Hugging Face · google/embeddinggemma-2","u":"https://huggingface.co/google/embeddinggemma-2"},{"t":"config.json","u":"https://huggingface.co/google/embeddinggemma-2/blob/main/config.json"},{"t":"Ollama library · embeddinggemma-2","u":"https://ollama.com/library/embeddinggemma-2"}],"page":"https://aimap.page/en/models/compute/open-models/embeddinggemma-2/"},{"id":"functiongemma-270m-it","name":"functiongemma-270m-it","hf":"google/functiongemma-270m-it","org":"google","family":"gemma","series":"functiongemma","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-10-08","updated":"2026-01-14","gated":true,"params":{"total":0.268,"active":null,"src":"safetensors","q":null,"stTotal":0.268},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.54,"t":1.1},"fp8":{"w":0.28,"t":0.8},"q4":{"w":0.16,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.54,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"functiongemma:270m","url":"https://ollama.com/library/functiongemma"}],"variants":[{"id":"google/functiongemma-270m-it","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/functiongemma-270m-it","u":"https://huggingface.co/google/functiongemma-270m-it"},{"t":"Ollama library · functiongemma","u":"https://ollama.com/library/functiongemma"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-functiongemma-270m-it"},{"id":"gemma-2-2b-it","name":"gemma-2-2b-it","hf":"google/gemma-2-2b-it","org":"google","family":"gemma","series":"gemma-2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-07-16","updated":"2024-08-27","gated":true,"params":{"total":2.614,"active":null,"src":"safetensors","q":null,"stTotal":2.614},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":5.23,"t":6.3},"fp8":{"w":2.78,"t":3.6},"q4":{"w":1.58,"t":2.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.23,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"gemma2:2b","url":"https://ollama.com/library/gemma2"}],"variants":[{"id":"google/gemma-2-2b-it","kind":"Instruct"},{"id":"google/gemma-2-2b","kind":"main"},{"id":"google/gemma-2-2b-it-GGUF","kind":"Instruct/GGUF"},{"id":"google/gemma-2-2b-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · google/gemma-2-2b-it","u":"https://huggingface.co/google/gemma-2-2b-it"},{"t":"Ollama library · gemma2","u":"https://ollama.com/library/gemma2"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-2-2b-it"},{"id":"gemma-2-9b-it","name":"gemma-2-9b-it","hf":"google/gemma-2-9b-it","org":"google","family":"gemma","series":"gemma-2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-06-24","updated":"2024-08-27","gated":true,"params":{"total":9.242,"active":null,"src":"safetensors","q":null,"stTotal":9.242},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":18.48,"t":20.8},"fp8":{"w":9.82,"t":11.3},"q4":{"w":5.6,"t":6.7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":18.48,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gemma2:9b","url":"https://ollama.com/library/gemma2"}],"variants":[{"id":"google/gemma-2-9b-it","kind":"Instruct"},{"id":"google/gemma-2-9b","kind":"main"}],"sources":[{"t":"Hugging Face · google/gemma-2-9b-it","u":"https://huggingface.co/google/gemma-2-9b-it"},{"t":"Ollama library · gemma2","u":"https://ollama.com/library/gemma2"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-2-9b-it"},{"id":"gemma-2-27b-it","name":"gemma-2-27b-it","hf":"google/gemma-2-27b-it","org":"google","family":"gemma","series":"gemma-2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-06-24","updated":"2024-08-27","gated":true,"params":{"total":27.227,"active":null,"src":"safetensors","q":null,"stTotal":27.227},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":54.45,"t":60.4},"fp8":{"w":28.93,"t":32.3},"q4":{"w":16.51,"t":18.7}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":54.45,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gemma2:27b","url":"https://ollama.com/library/gemma2"}],"variants":[{"id":"google/gemma-2-27b-it","kind":"Instruct"},{"id":"google/gemma-2-27b","kind":"main"}],"sources":[{"t":"Hugging Face · google/gemma-2-27b-it","u":"https://huggingface.co/google/gemma-2-27b-it"},{"t":"Ollama library · gemma2","u":"https://ollama.com/library/gemma2"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-2-27b-it"},{"id":"gemma-2-2b-jpn-it","name":"gemma-2-2b-jpn-it","hf":"google/gemma-2-2b-jpn-it","org":"google","family":"gemma","series":"gemma-2-jpn","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-25","updated":"2024-10-02","gated":true,"params":{"total":2.614,"active":null,"src":"safetensors","q":null,"stTotal":2.614},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":5.23,"t":6.3},"fp8":{"w":2.78,"t":3.6},"q4":{"w":1.58,"t":2.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.23,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/gemma-2-2b-jpn-it","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/gemma-2-2b-jpn-it","u":"https://huggingface.co/google/gemma-2-2b-jpn-it"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-2-2b-jpn-it"},{"id":"gemma-3-270m-it","name":"gemma-3-270m-it","hf":"google/gemma-3-270m-it","org":"google","family":"gemma","series":"gemma-3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-30","updated":"2025-08-14","gated":true,"params":{"total":0.268,"active":null,"src":"safetensors","q":null,"stTotal":0.268},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.54,"t":1.1},"fp8":{"w":0.28,"t":0.8},"q4":{"w":0.16,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.54,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gemma3:270m","url":"https://ollama.com/library/gemma3"}],"variants":[{"id":"google/gemma-3-270m-it","kind":"Instruct"},{"id":"google/gemma-3-270m","kind":"main"}],"sources":[{"t":"Hugging Face · google/gemma-3-270m-it","u":"https://huggingface.co/google/gemma-3-270m-it"},{"t":"Ollama library · gemma3","u":"https://ollama.com/library/gemma3"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-3-270m-it"},{"id":"gemma-3-1b-it","name":"gemma-3-1b-it","hf":"google/gemma-3-1b-it","org":"google","family":"gemma","series":"gemma-3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-03-10","updated":"2025-04-04","gated":true,"params":{"total":1,"active":null,"src":"safetensors","q":null,"stTotal":1},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":2,"t":2.7},"fp8":{"w":1.06,"t":1.7},"q4":{"w":0.61,"t":1.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"gemma3:1b","url":"https://ollama.com/library/gemma3"}],"variants":[{"id":"google/gemma-3-1b-it","kind":"Instruct"},{"id":"google/gemma-3-1b-pt","kind":"Base"},{"id":"google/gemma-3-1b-it-qat-q4_0-gguf","kind":"Instruct/GGUF"},{"id":"google/gemma-3-1b-it-qat-int4-unquantized","kind":"Instruct/INT4"},{"id":"google/gemma-3-1b-pt-qat-q4_0-gguf","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · google/gemma-3-1b-it","u":"https://huggingface.co/google/gemma-3-1b-it"},{"t":"Ollama library · gemma3","u":"https://ollama.com/library/gemma3"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-3-1b-it"},{"id":"gemma-3-4b-it","name":"gemma-3-4b-it","hf":"google/gemma-3-4b-it","org":"google","family":"gemma","series":"gemma-3","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-02-20","updated":"2025-03-21","gated":true,"params":{"total":4.3,"active":null,"src":"safetensors","q":null,"stTotal":4.3},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":8.6,"t":10},"fp8":{"w":4.57,"t":5.5},"q4":{"w":2.61,"t":3.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.6,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"gemma3:4b","url":"https://ollama.com/library/gemma3"}],"variants":[{"id":"google/gemma-3-4b-it","kind":"Instruct"},{"id":"google/gemma-3-4b-pt","kind":"Base"},{"id":"google/gemma-3-4b-it-qat-q4_0-gguf","kind":"Instruct/GGUF"},{"id":"google/gemma-3-4b-it-qat-int4-unquantized","kind":"Instruct/INT4"},{"id":"google/gemma-3-4b-pt-qat-q4_0-gguf","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · google/gemma-3-4b-it","u":"https://huggingface.co/google/gemma-3-4b-it"},{"t":"Ollama library · gemma3","u":"https://ollama.com/library/gemma3"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-3-4b-it"},{"id":"gemma-3-12b-it","name":"gemma-3-12b-it","hf":"google/gemma-3-12b-it","org":"google","family":"gemma","series":"gemma-3","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-03-01","updated":"2025-03-21","gated":true,"params":{"total":12.187,"active":null,"src":"safetensors","q":null,"stTotal":12.187},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":24.37,"t":27.3},"fp8":{"w":12.95,"t":14.7},"q4":{"w":7.39,"t":8.6}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24.37,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"gemma3:12b","url":"https://ollama.com/library/gemma3"}],"variants":[{"id":"google/gemma-3-12b-it","kind":"Instruct"},{"id":"google/gemma-3-12b-pt","kind":"Base"},{"id":"google/gemma-3-12b-it-qat-q4_0-gguf","kind":"Instruct/GGUF"},{"id":"google/gemma-3-12b-it-qat-int4-unquantized","kind":"Instruct/INT4"},{"id":"google/gemma-3-12b-pt-qat-q4_0-gguf","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · google/gemma-3-12b-it","u":"https://huggingface.co/google/gemma-3-12b-it"},{"t":"Ollama library · gemma3","u":"https://ollama.com/library/gemma3"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-3-12b-it"},{"id":"gemma-3-27b-it","name":"gemma-3-27b-it","hf":"google/gemma-3-27b-it","org":"google","family":"gemma","series":"gemma-3","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-03-01","updated":"2025-03-21","gated":true,"params":{"total":27.432,"active":null,"src":"safetensors","q":null,"stTotal":27.432},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":54.86,"t":60.9},"fp8":{"w":29.15,"t":32.6},"q4":{"w":16.63,"t":18.8}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":54.86,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"gemma3:27b","url":"https://ollama.com/library/gemma3"}],"variants":[{"id":"google/gemma-3-27b-it","kind":"Instruct"},{"id":"google/gemma-3-27b-pt","kind":"Base"},{"id":"google/gemma-3-27b-it-qat-q4_0-gguf","kind":"Instruct/GGUF"},{"id":"google/gemma-3-27b-pt-qat-q4_0-gguf","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · google/gemma-3-27b-it","u":"https://huggingface.co/google/gemma-3-27b-it"},{"t":"Ollama library · gemma3","u":"https://ollama.com/library/gemma3"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-3-27b-it"},{"id":"gemma-3-12b-it-qat-q4-0-unquantized","name":"gemma-3-12b-it-qat-q4_0-unquantized","hf":"google/gemma-3-12b-it-qat-q4_0-unquantized","org":"google","family":"gemma","series":"gemma-3-qat-q4_0-unquantized","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-04-08","updated":"2025-04-15","gated":true,"params":{"total":12.187,"active":null,"src":"safetensors","q":null,"stTotal":12.187},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":24.37,"t":27.3},"fp8":{"w":12.95,"t":14.7},"q4":{"w":7.39,"t":8.6}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24.37,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/gemma-3-12b-it-qat-q4_0-unquantized","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/gemma-3-12b-it-qat-q4_0-unquantized","u":"https://huggingface.co/google/gemma-3-12b-it-qat-q4_0-unquantized"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-3-12b-it-qat-q4-0-unquantized"},{"id":"gemma-3n-e2b-it","name":"gemma-3n-E2B-it","hf":"google/gemma-3n-E2B-it","org":"google","family":"gemma","series":"gemma-3n","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-06-12","updated":"2025-07-14","gated":true,"params":{"total":5.439,"active":null,"src":"safetensors","q":null,"stTotal":5.439},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":10.88,"t":12.5},"fp8":{"w":5.78,"t":6.9},"q4":{"w":3.3,"t":4.1}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":10.88,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gemma3n:e2b","url":"https://ollama.com/library/gemma3n"}],"variants":[{"id":"google/gemma-3n-E2B-it","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/gemma-3n-E2B-it","u":"https://huggingface.co/google/gemma-3n-E2B-it"},{"t":"Ollama library · gemma3n","u":"https://ollama.com/library/gemma3n"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-3n-e2b-it"},{"id":"gemma-3n-e4b-it","name":"gemma-3n-E4B-it","hf":"google/gemma-3n-E4B-it","org":"google","family":"gemma","series":"gemma-3n","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-06-03","updated":"2025-07-14","gated":true,"params":{"total":7.85,"active":null,"src":"safetensors","q":null,"stTotal":7.85},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":15.7,"t":17.8},"fp8":{"w":8.34,"t":9.7},"q4":{"w":4.76,"t":5.7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.7,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gemma3n:e4b","url":"https://ollama.com/library/gemma3n"}],"variants":[{"id":"google/gemma-3n-E4B-it","kind":"Instruct"},{"id":"google/gemma-3n-E4B","kind":"main"}],"sources":[{"t":"Hugging Face · google/gemma-3n-E4B-it","u":"https://huggingface.co/google/gemma-3n-E4B-it"},{"t":"Ollama library · gemma3n","u":"https://ollama.com/library/gemma3n"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-3n-e4b-it"},{"id":"gemma-4-e2b-it","name":"gemma-4-E2B-it","hf":"google/gemma-4-E2B-it","org":"google","family":"gemma","series":"gemma-4","task":"omni","pipeline":"any-to-any","tags":[],"released":"2026-03-02","updated":"2026-07-20","gated":false,"params":{"total":5.123,"active":null,"src":"safetensors","q":null,"stTotal":5.123},"moe":false,"ctx":131072,"arch":{"L":35,"attn":7,"slide":28,"win":512,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.07,"32768":0.25,"131072":0.95},"mem":{"bf16":{"w":10.25,"t":11.8},"fp8":{"w":5.44,"t":6.6},"q4":{"w":3.11,"t":4}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":10.25,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://ai.google.dev/gemma/docs/gemma_4_license","cls":"open"},"runtimes":[{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gemma4:e2b","url":"https://ollama.com/library/gemma4"}],"variants":[{"id":"google/gemma-4-E2B-it","kind":"Instruct"},{"id":"google/gemma-4-E2B","kind":"main"},{"id":"google/gemma-4-E2B-it-qat-mobile-transformers","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/gemma-4-E2B-it","u":"https://huggingface.co/google/gemma-4-E2B-it"},{"t":"config.json","u":"https://huggingface.co/google/gemma-4-E2B-it/blob/main/config.json"},{"t":"License","u":"https://ai.google.dev/gemma/docs/gemma_4_license"},{"t":"Ollama library · gemma4","u":"https://ollama.com/library/gemma4"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-4-e2b-it"},{"id":"gemma-4-e4b-it","name":"gemma-4-E4B-it","hf":"google/gemma-4-E4B-it","org":"google","family":"gemma","series":"gemma-4","task":"omni","pipeline":"any-to-any","tags":[],"released":"2026-03-02","updated":"2026-07-20","gated":false,"params":{"total":7.996,"active":null,"src":"safetensors","q":null,"stTotal":7.996},"moe":false,"ctx":131072,"arch":{"L":42,"attn":7,"slide":35,"win":512,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.15,"32768":0.51,"131072":1.92},"mem":{"bf16":{"w":15.99,"t":18.2},"fp8":{"w":8.5,"t":10},"q4":{"w":4.85,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.99,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://ai.google.dev/gemma/docs/gemma_4_license","cls":"open"},"runtimes":[{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gemma4:e4b","url":"https://ollama.com/library/gemma4"}],"variants":[{"id":"google/gemma-4-E4B-it","kind":"Instruct"},{"id":"google/gemma-4-E4B","kind":"main"},{"id":"google/gemma-4-E4B-it-qat-mobile-transformers","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/gemma-4-E4B-it","u":"https://huggingface.co/google/gemma-4-E4B-it"},{"t":"config.json","u":"https://huggingface.co/google/gemma-4-E4B-it/blob/main/config.json"},{"t":"License","u":"https://ai.google.dev/gemma/docs/gemma_4_license"},{"t":"Ollama library · gemma4","u":"https://ollama.com/library/gemma4"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-4-e4b-it"},{"id":"gemma-4-12b-it","name":"gemma-4-12B-it","hf":"google/gemma-4-12B-it","org":"google","family":"gemma","series":"gemma-4","task":"omni","pipeline":"any-to-any","tags":[],"released":"2026-05-23","updated":"2026-07-20","gated":false,"params":{"total":11.96,"active":null,"src":"safetensors","q":null,"stTotal":11.96},"moe":false,"ctx":262144,"arch":{"L":48,"attn":8,"slide":40,"win":1024,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.87,"32768":2.48,"131072":8.93},"mem":{"bf16":{"w":23.92,"t":27.7},"fp8":{"w":12.71,"t":15.3},"q4":{"w":7.25,"t":9.3}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":23.92,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://ai.google.dev/gemma/docs/gemma_4_license","cls":"open"},"runtimes":[{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gemma4:12b","url":"https://ollama.com/library/gemma4"}],"variants":[{"id":"google/gemma-4-12B-it","kind":"Instruct"},{"id":"google/gemma-4-12B","kind":"main"}],"sources":[{"t":"Hugging Face · google/gemma-4-12B-it","u":"https://huggingface.co/google/gemma-4-12B-it"},{"t":"config.json","u":"https://huggingface.co/google/gemma-4-12B-it/blob/main/config.json"},{"t":"License","u":"https://ai.google.dev/gemma/docs/gemma_4_license"},{"t":"Ollama library · gemma4","u":"https://ollama.com/library/gemma4"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-4-12b-it"},{"id":"gemma-4-26b-a4b-it","name":"gemma-4-26B-A4B-it","hf":"google/gemma-4-26B-A4B-it","org":"google","family":"gemma","series":"gemma-4","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-03-11","updated":"2026-07-20","gated":false,"params":{"total":25.806,"active":4,"src":"safetensors","q":null,"stTotal":25.806},"moe":true,"ctx":262144,"arch":{"L":30,"attn":5,"slide":25,"win":1024,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.55,"32768":1.55,"131072":5.58},"mem":{"bf16":{"w":51.61,"t":57.8},"fp8":{"w":27.42,"t":31.2},"q4":{"w":15.64,"t":18.3}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":51.61,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://ai.google.dev/gemma/docs/gemma_4_license","cls":"open"},"runtimes":[{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gemma4:26b-a4b","url":"https://ollama.com/library/gemma4"}],"variants":[{"id":"google/gemma-4-26B-A4B-it","kind":"Instruct"},{"id":"google/gemma-4-26B-A4B","kind":"main"}],"sources":[{"t":"Hugging Face · google/gemma-4-26B-A4B-it","u":"https://huggingface.co/google/gemma-4-26B-A4B-it"},{"t":"config.json","u":"https://huggingface.co/google/gemma-4-26B-A4B-it/blob/main/config.json"},{"t":"License","u":"https://ai.google.dev/gemma/docs/gemma_4_license"},{"t":"Ollama library · gemma4","u":"https://ollama.com/library/gemma4"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-4-26b-a4b-it"},{"id":"gemma-4-31b-it","name":"gemma-4-31B-it","hf":"google/gemma-4-31B-it","org":"google","family":"gemma","series":"gemma-4","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-03-11","updated":"2026-07-20","gated":false,"params":{"total":31.273,"active":null,"src":"safetensors","q":null,"stTotal":31.273},"moe":false,"ctx":262144,"arch":{"L":60,"attn":10,"slide":50,"win":1024,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.18,"32768":6.21,"131072":22.31},"mem":{"bf16":{"w":62.55,"t":71.5},"fp8":{"w":33.23,"t":39.2},"q4":{"w":18.96,"t":23.5}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":62.55,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://ai.google.dev/gemma/docs/gemma_4_license","cls":"open"},"runtimes":[{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gemma4:31b","url":"https://ollama.com/library/gemma4"}],"variants":[{"id":"google/gemma-4-31B-it","kind":"Instruct"},{"id":"google/gemma-4-31B","kind":"main"}],"sources":[{"t":"Hugging Face · google/gemma-4-31B-it","u":"https://huggingface.co/google/gemma-4-31B-it"},{"t":"config.json","u":"https://huggingface.co/google/gemma-4-31B-it/blob/main/config.json"},{"t":"License","u":"https://ai.google.dev/gemma/docs/gemma_4_license"},{"t":"Ollama library · gemma4","u":"https://ollama.com/library/gemma4"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-4-31b-it"},{"id":"gemma-4-e2b-it-qat-q4-0-unquantized","name":"gemma-4-E2B-it-qat-q4_0-unquantized","hf":"google/gemma-4-E2B-it-qat-q4_0-unquantized","org":"google","family":"gemma","series":"gemma-4-qat-q4_0-unquantized","task":"omni","pipeline":"any-to-any","tags":[],"released":"2026-04-29","updated":"2026-07-20","gated":false,"params":{"total":5.104,"active":null,"src":"safetensors","q":null,"stTotal":5.104},"moe":false,"ctx":131072,"arch":{"L":35,"attn":7,"slide":28,"win":512,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.07,"32768":0.25,"131072":0.95},"mem":{"bf16":{"w":10.21,"t":11.8},"fp8":{"w":5.42,"t":6.5},"q4":{"w":3.09,"t":4}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":10.21,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://ai.google.dev/gemma/docs/gemma_4_license","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"google/gemma-4-E2B-it-qat-w4a16-ct","kind":"Instruct/W4A16"},{"id":"google/gemma-4-E2B-it-qat-q4_0-gguf","kind":"Instruct/GGUF"},{"id":"google/gemma-4-E2B-it-qat-q4_0-unquantized","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/gemma-4-E2B-it-qat-q4_0-unquantized","u":"https://huggingface.co/google/gemma-4-E2B-it-qat-q4_0-unquantized"},{"t":"config.json","u":"https://huggingface.co/google/gemma-4-E2B-it-qat-q4_0-unquantized/blob/main/config.json"},{"t":"License","u":"https://ai.google.dev/gemma/docs/gemma_4_license"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-4-e2b-it-qat-q4-0-unquantized"},{"id":"gemma-4-e4b-it-qat-q4-0-unquantized","name":"gemma-4-E4B-it-qat-q4_0-unquantized","hf":"google/gemma-4-E4B-it-qat-q4_0-unquantized","org":"google","family":"gemma","series":"gemma-4-qat-q4_0-unquantized","task":"omni","pipeline":"any-to-any","tags":[],"released":"2026-04-30","updated":"2026-07-20","gated":false,"params":{"total":7.941,"active":null,"src":"safetensors","q":null,"stTotal":7.941},"moe":false,"ctx":131072,"arch":{"L":42,"attn":7,"slide":35,"win":512,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.15,"32768":0.51,"131072":1.92},"mem":{"bf16":{"w":15.88,"t":18.1},"fp8":{"w":8.44,"t":9.9},"q4":{"w":4.81,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.88,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://ai.google.dev/gemma/docs/gemma_4_license","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"google/gemma-4-E4B-it-qat-q4_0-gguf","kind":"Instruct/GGUF"},{"id":"google/gemma-4-E4B-it-qat-w4a16-ct","kind":"Instruct/W4A16"},{"id":"google/gemma-4-E4B-it-qat-q4_0-unquantized","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/gemma-4-E4B-it-qat-q4_0-unquantized","u":"https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-unquantized"},{"t":"config.json","u":"https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-unquantized/blob/main/config.json"},{"t":"License","u":"https://ai.google.dev/gemma/docs/gemma_4_license"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-4-e4b-it-qat-q4-0-unquantized"},{"id":"gemma-4-12b-it-qat-q4-0-unquantized","name":"gemma-4-12B-it-qat-q4_0-unquantized","hf":"google/gemma-4-12B-it-qat-q4_0-unquantized","org":"google","family":"gemma","series":"gemma-4-qat-q4_0-unquantized","task":"omni","pipeline":"any-to-any","tags":[],"released":"2026-06-04","updated":"2026-07-20","gated":false,"params":{"total":11.96,"active":null,"src":"safetensors","q":null,"stTotal":11.96},"moe":false,"ctx":262144,"arch":{"L":48,"attn":8,"slide":40,"win":1024,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.87,"32768":2.48,"131072":8.93},"mem":{"bf16":{"w":23.92,"t":27.7},"fp8":{"w":12.71,"t":15.3},"q4":{"w":7.25,"t":9.3}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":23.92,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://ai.google.dev/gemma/docs/gemma_4_license","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"google/gemma-4-12B-it-qat-w4a16-ct","kind":"Instruct/W4A16"},{"id":"google/gemma-4-12B-it-qat-q4_0-gguf","kind":"Instruct/GGUF"},{"id":"google/gemma-4-12B-it-qat-q4_0-unquantized","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/gemma-4-12B-it-qat-q4_0-unquantized","u":"https://huggingface.co/google/gemma-4-12B-it-qat-q4_0-unquantized"},{"t":"config.json","u":"https://huggingface.co/google/gemma-4-12B-it-qat-q4_0-unquantized/blob/main/config.json"},{"t":"License","u":"https://ai.google.dev/gemma/docs/gemma_4_license"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-4-12b-it-qat-q4-0-unquantized"},{"id":"gemma-4-26b-a4b-it-qat-q4-0-unquantized","name":"gemma-4-26B-A4B-it-qat-q4_0-unquantized","hf":"google/gemma-4-26B-A4B-it-qat-q4_0-unquantized","org":"google","family":"gemma","series":"gemma-4-qat-q4_0-unquantized","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-04-29","updated":"2026-07-20","gated":false,"params":{"total":25.806,"active":4,"src":"safetensors","q":null,"stTotal":25.806},"moe":true,"ctx":262144,"arch":{"L":30,"attn":5,"slide":25,"win":1024,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.55,"32768":1.55,"131072":5.58},"mem":{"bf16":{"w":51.61,"t":57.8},"fp8":{"w":27.42,"t":31.2},"q4":{"w":15.64,"t":18.3}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":51.61,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://ai.google.dev/gemma/docs/gemma_4_license","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"google/gemma-4-26B-A4B-it-qat-q4_0-gguf","kind":"Instruct/GGUF"},{"id":"google/gemma-4-26B-A4B-it-qat-q4_0-unquantized","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/gemma-4-26B-A4B-it-qat-q4_0-unquantized","u":"https://huggingface.co/google/gemma-4-26B-A4B-it-qat-q4_0-unquantized"},{"t":"config.json","u":"https://huggingface.co/google/gemma-4-26B-A4B-it-qat-q4_0-unquantized/blob/main/config.json"},{"t":"License","u":"https://ai.google.dev/gemma/docs/gemma_4_license"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-4-26b-a4b-it-qat-q4-0-unquantized"},{"id":"gemma-4-31b-it-qat-q4-0-unquantized","name":"gemma-4-31B-it-qat-q4_0-unquantized","hf":"google/gemma-4-31B-it-qat-q4_0-unquantized","org":"google","family":"gemma","series":"gemma-4-qat-q4_0-unquantized","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-04-28","updated":"2026-07-20","gated":false,"params":{"total":31.273,"active":null,"src":"safetensors","q":null,"stTotal":31.273},"moe":false,"ctx":262144,"arch":{"L":60,"attn":10,"slide":50,"win":1024,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.18,"32768":6.21,"131072":22.31},"mem":{"bf16":{"w":62.55,"t":71.5},"fp8":{"w":33.23,"t":39.2},"q4":{"w":18.96,"t":23.5}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":62.55,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://ai.google.dev/gemma/docs/gemma_4_license","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"google/gemma-4-31B-it-qat-w4a16-ct","kind":"Instruct/W4A16"},{"id":"google/gemma-4-31B-it-qat-q4_0-unquantized","kind":"Instruct"},{"id":"google/gemma-4-31B-it-qat-q4_0-gguf","kind":"Instruct/GGUF"}],"sources":[{"t":"Hugging Face · google/gemma-4-31B-it-qat-q4_0-unquantized","u":"https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-unquantized"},{"t":"config.json","u":"https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-unquantized/blob/main/config.json"},{"t":"License","u":"https://ai.google.dev/gemma/docs/gemma_4_license"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-gemma-4-31b-it-qat-q4-0-unquantized"},{"id":"medgemma-4b-it","name":"medgemma-4b-it","hf":"google/medgemma-4b-it","org":"google","family":"gemma","series":"medgemma","task":"vlm","pipeline":"image-text-to-text","tags":["medical"],"released":"2025-05-19","updated":"2025-10-28","gated":true,"params":{"total":4.3,"active":null,"src":"safetensors","q":null,"stTotal":4.3},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":8.6,"t":10},"fp8":{"w":4.57,"t":5.5},"q4":{"w":2.61,"t":3.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.6,"native":"BF16","license":{"id":"health-ai-developer-foundations","name":"health-ai-developer-foundations","link":"https://developers.google.com/health-ai-developer-foundations/terms","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"medgemma:4b","url":"https://ollama.com/library/medgemma"}],"variants":[{"id":"google/medgemma-4b-it","kind":"Instruct"},{"id":"google/medgemma-4b-pt","kind":"Base"}],"sources":[{"t":"Hugging Face · google/medgemma-4b-it","u":"https://huggingface.co/google/medgemma-4b-it"},{"t":"License","u":"https://developers.google.com/health-ai-developer-foundations/terms"},{"t":"Ollama library · medgemma","u":"https://ollama.com/library/medgemma"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-medgemma-4b-it"},{"id":"medgemma-27b-it","name":"medgemma-27b-it","hf":"google/medgemma-27b-it","org":"google","family":"gemma","series":"medgemma","task":"vlm","pipeline":"image-text-to-text","tags":["medical"],"released":"2025-07-09","updated":"2025-07-10","gated":true,"params":{"total":27.432,"active":null,"src":"safetensors","q":null,"stTotal":27.432},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":54.86,"t":60.9},"fp8":{"w":29.15,"t":32.6},"q4":{"w":16.63,"t":18.8}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":54.86,"native":"BF16","license":{"id":"health-ai-developer-foundations","name":"health-ai-developer-foundations","link":"https://developers.google.com/health-ai-developer-foundations/terms","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"medgemma:27b","url":"https://ollama.com/library/medgemma"}],"variants":[{"id":"google/medgemma-27b-it","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/medgemma-27b-it","u":"https://huggingface.co/google/medgemma-27b-it"},{"t":"License","u":"https://developers.google.com/health-ai-developer-foundations/terms"},{"t":"Ollama library · medgemma","u":"https://ollama.com/library/medgemma"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-medgemma-27b-it"},{"id":"medgemma-1-5-4b-it","name":"medgemma-1.5-4b-it","hf":"google/medgemma-1.5-4b-it","org":"google","family":"gemma","series":"medgemma-1.5","task":"vlm","pipeline":"image-text-to-text","tags":["medical"],"released":"2026-01-07","updated":"2026-04-13","gated":true,"params":{"total":4.3,"active":null,"src":"safetensors","q":null,"stTotal":4.3},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":8.6,"t":10},"fp8":{"w":4.57,"t":5.5},"q4":{"w":2.61,"t":3.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.6,"native":"BF16","license":{"id":"health-ai-developer-foundations","name":"health-ai-developer-foundations","link":"https://developers.google.com/health-ai-developer-foundations/terms","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"medgemma1.5:4b","url":"https://ollama.com/library/medgemma1.5"}],"variants":[{"id":"google/medgemma-1.5-4b-it","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/medgemma-1.5-4b-it","u":"https://huggingface.co/google/medgemma-1.5-4b-it"},{"t":"License","u":"https://developers.google.com/health-ai-developer-foundations/terms"},{"t":"Ollama library · medgemma1.5","u":"https://ollama.com/library/medgemma1.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-medgemma-1-5-4b-it"},{"id":"medgemma-27b-text-it","name":"medgemma-27b-text-it","hf":"google/medgemma-27b-text-it","org":"google","family":"gemma","series":"medgemma-text","task":"llm","pipeline":"text-generation","tags":["medical"],"released":"2025-05-19","updated":"2025-09-16","gated":true,"params":{"total":27.009,"active":null,"src":"safetensors","q":null,"stTotal":27.009},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":54.02,"t":59.9},"fp8":{"w":28.7,"t":32.1},"q4":{"w":16.37,"t":18.5}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":54.02,"native":"BF16","license":{"id":"health-ai-developer-foundations","name":"health-ai-developer-foundations","link":"https://developers.google.com/health-ai-developer-foundations/terms","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/medgemma-27b-text-it","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/medgemma-27b-text-it","u":"https://huggingface.co/google/medgemma-27b-text-it"},{"t":"License","u":"https://developers.google.com/health-ai-developer-foundations/terms"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-medgemma-27b-text-it"},{"id":"paligemma2-3b-pt-224","name":"paligemma2-3b-pt-224","hf":"google/paligemma2-3b-pt-224","org":"google","family":"gemma","series":"paligemma2-224","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-11-21","updated":"2024-12-05","gated":true,"params":{"total":3.032,"active":null,"src":"safetensors","q":null,"stTotal":3.032},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":6.06,"t":7.2},"fp8":{"w":3.22,"t":4},"q4":{"w":1.84,"t":2.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.06,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/paligemma2-3b-pt-224","kind":"Base"}],"sources":[{"t":"Hugging Face · google/paligemma2-3b-pt-224","u":"https://huggingface.co/google/paligemma2-3b-pt-224"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-paligemma2-3b-pt-224"},{"id":"paligemma2-3b-pt-448","name":"paligemma2-3b-pt-448","hf":"google/paligemma2-3b-pt-448","org":"google","family":"gemma","series":"paligemma2-448","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-11-21","updated":"2024-12-05","gated":true,"params":{"total":3.033,"active":null,"src":"safetensors","q":null,"stTotal":3.033},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":6.07,"t":7.2},"fp8":{"w":3.22,"t":4},"q4":{"w":1.84,"t":2.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.07,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/paligemma2-3b-pt-448","kind":"Base"}],"sources":[{"t":"Hugging Face · google/paligemma2-3b-pt-448","u":"https://huggingface.co/google/paligemma2-3b-pt-448"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-paligemma2-3b-pt-448"},{"id":"paligemma2-3b-ft-docci-448","name":"paligemma2-3b-ft-docci-448","hf":"google/paligemma2-3b-ft-docci-448","org":"google","family":"gemma","series":"paligemma2-ft-docci-448","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-11-21","updated":"2024-12-05","gated":true,"params":{"total":3.033,"active":null,"src":"safetensors","q":null,"stTotal":3.033},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":6.07,"t":7.2},"fp8":{"w":3.22,"t":4},"q4":{"w":1.84,"t":2.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.07,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/paligemma2-3b-ft-docci-448","kind":"main"}],"sources":[{"t":"Hugging Face · google/paligemma2-3b-ft-docci-448","u":"https://huggingface.co/google/paligemma2-3b-ft-docci-448"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-paligemma2-3b-ft-docci-448"},{"id":"paligemma2-10b-ft-docci-448","name":"paligemma2-10b-ft-docci-448","hf":"google/paligemma2-10b-ft-docci-448","org":"google","family":"gemma","series":"paligemma2-ft-docci-448","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-11-21","updated":"2024-12-05","gated":true,"params":{"total":9.664,"active":null,"src":"safetensors","q":null,"stTotal":9.664},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":19.33,"t":21.8},"fp8":{"w":10.27,"t":11.8},"q4":{"w":5.86,"t":6.9}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":19.33,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/paligemma2-10b-ft-docci-448","kind":"main"}],"sources":[{"t":"Hugging Face · google/paligemma2-10b-ft-docci-448","u":"https://huggingface.co/google/paligemma2-10b-ft-docci-448"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-paligemma2-10b-ft-docci-448"},{"id":"paligemma2-3b-mix-224","name":"paligemma2-3b-mix-224","hf":"google/paligemma2-3b-mix-224","org":"google","family":"gemma","series":"paligemma2-mix-224","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-11-21","updated":"2025-02-07","gated":true,"params":{"total":3.032,"active":null,"src":"safetensors","q":null,"stTotal":3.032},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":6.06,"t":7.2},"fp8":{"w":3.22,"t":4},"q4":{"w":1.84,"t":2.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.06,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/paligemma2-3b-mix-224","kind":"main"}],"sources":[{"t":"Hugging Face · google/paligemma2-3b-mix-224","u":"https://huggingface.co/google/paligemma2-3b-mix-224"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-paligemma2-3b-mix-224"},{"id":"paligemma2-3b-mix-448","name":"paligemma2-3b-mix-448","hf":"google/paligemma2-3b-mix-448","org":"google","family":"gemma","series":"paligemma2-mix-448","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-11-21","updated":"2025-02-07","gated":true,"params":{"total":3.033,"active":null,"src":"safetensors","q":null,"stTotal":3.033},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":6.07,"t":7.2},"fp8":{"w":3.22,"t":4},"q4":{"w":1.84,"t":2.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.07,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/paligemma2-3b-mix-448","kind":"main"}],"sources":[{"t":"Hugging Face · google/paligemma2-3b-mix-448","u":"https://huggingface.co/google/paligemma2-3b-mix-448"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-paligemma2-3b-mix-448"},{"id":"shieldgemma-9b","name":"shieldgemma-9b","hf":"google/shieldgemma-9b","org":"google","family":"gemma","series":"shieldgemma","task":"guard","pipeline":"text-generation","tags":[],"released":"2024-07-16","updated":"2024-09-06","gated":true,"params":{"total":9.242,"active":null,"src":"safetensors","q":null,"stTotal":9.242},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":18.48,"t":20.8},"fp8":{"w":9.82,"t":11.3},"q4":{"w":5.6,"t":6.7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":18.48,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"shieldgemma:9b","url":"https://ollama.com/library/shieldgemma"}],"variants":[{"id":"google/shieldgemma-9b","kind":"main"}],"sources":[{"t":"Hugging Face · google/shieldgemma-9b","u":"https://huggingface.co/google/shieldgemma-9b"},{"t":"Ollama library · shieldgemma","u":"https://ollama.com/library/shieldgemma"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-shieldgemma-9b"},{"id":"shieldgemma-2-4b-it","name":"shieldgemma-2-4b-it","hf":"google/shieldgemma-2-4b-it","org":"google","family":"gemma","series":"shieldgemma-2","task":"guard","pipeline":"image-text-to-text","tags":[],"released":"2025-03-04","updated":"2025-04-04","gated":true,"params":{"total":4.3,"active":null,"src":"safetensors","q":null,"stTotal":4.3},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":8.6,"t":10},"fp8":{"w":4.57,"t":5.5},"q4":{"w":2.61,"t":3.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.6,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/shieldgemma-2-4b-it","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/shieldgemma-2-4b-it","u":"https://huggingface.co/google/shieldgemma-2-4b-it"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-shieldgemma-2-4b-it"},{"id":"t5gemma-2-270m-270m","name":"t5gemma-2-270m-270m","hf":"google/t5gemma-2-270m-270m","org":"google","family":"gemma","series":"t5gemma-2","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-10-25","updated":"2025-12-16","gated":true,"params":{"total":0.786,"active":null,"src":"safetensors","q":null,"stTotal":0.786},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.57,"t":2.2},"fp8":{"w":0.84,"t":1.4},"q4":{"w":0.48,"t":1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.57,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/t5gemma-2-270m-270m","kind":"main"}],"sources":[{"t":"Hugging Face · google/t5gemma-2-270m-270m","u":"https://huggingface.co/google/t5gemma-2-270m-270m"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-t5gemma-2-270m-270m"},{"id":"t5gemma-2-1b-1b","name":"t5gemma-2-1b-1b","hf":"google/t5gemma-2-1b-1b","org":"google","family":"gemma","series":"t5gemma-2","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-10-25","updated":"2025-12-18","gated":true,"params":{"total":2.116,"active":null,"src":"safetensors","q":null,"stTotal":2.116},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":4.23,"t":5.2},"fp8":{"w":2.25,"t":3},"q4":{"w":1.28,"t":1.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.23,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/t5gemma-2-1b-1b","kind":"main"}],"sources":[{"t":"Hugging Face · google/t5gemma-2-1b-1b","u":"https://huggingface.co/google/t5gemma-2-1b-1b"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-t5gemma-2-1b-1b"},{"id":"t5gemma-2-4b-4b","name":"t5gemma-2-4b-4b","hf":"google/t5gemma-2-4b-4b","org":"google","family":"gemma","series":"t5gemma-2","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-10-25","updated":"2025-12-18","gated":true,"params":{"total":7.509,"active":null,"src":"safetensors","q":null,"stTotal":7.509},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":15.02,"t":17},"fp8":{"w":7.98,"t":9.3},"q4":{"w":4.55,"t":5.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.02,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/t5gemma-2-4b-4b","kind":"main"}],"sources":[{"t":"Hugging Face · google/t5gemma-2-4b-4b","u":"https://huggingface.co/google/t5gemma-2-4b-4b"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-t5gemma-2-4b-4b"},{"id":"t5gemma-b-b-ul2","name":"t5gemma-b-b-ul2","hf":"google/t5gemma-b-b-ul2","org":"google","family":"gemma","series":"t5gemma-b-b-ul2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-19","updated":"2025-07-09","gated":true,"params":{"total":0.591,"active":null,"src":"safetensors","q":null,"stTotal":0.591},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.18,"t":1.8},"fp8":{"w":0.63,"t":1.2},"q4":{"w":0.36,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.18,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/t5gemma-b-b-ul2","kind":"main"}],"sources":[{"t":"Hugging Face · google/t5gemma-b-b-ul2","u":"https://huggingface.co/google/t5gemma-b-b-ul2"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-t5gemma-b-b-ul2"},{"id":"t5gemma-s-s-prefixlm","name":"t5gemma-s-s-prefixlm","hf":"google/t5gemma-s-s-prefixlm","org":"google","family":"gemma","series":"t5gemma-s-s-prefixlm","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-19","updated":"2025-07-09","gated":true,"params":{"total":0.313,"active":null,"src":"safetensors","q":null,"stTotal":0.313},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.63,"t":1.2},"fp8":{"w":0.33,"t":0.9},"q4":{"w":0.19,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.63,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/t5gemma-s-s-prefixlm","kind":"main"}],"sources":[{"t":"Hugging Face · google/t5gemma-s-s-prefixlm","u":"https://huggingface.co/google/t5gemma-s-s-prefixlm"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-t5gemma-s-s-prefixlm"},{"id":"t5gemma-s-s-ul2","name":"t5gemma-s-s-ul2","hf":"google/t5gemma-s-s-ul2","org":"google","family":"gemma","series":"t5gemma-s-s-ul2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-19","updated":"2025-07-09","gated":true,"params":{"total":0.313,"active":null,"src":"safetensors","q":null,"stTotal":0.313},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.63,"t":1.2},"fp8":{"w":0.33,"t":0.9},"q4":{"w":0.19,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.63,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/t5gemma-s-s-ul2","kind":"main"}],"sources":[{"t":"Hugging Face · google/t5gemma-s-s-ul2","u":"https://huggingface.co/google/t5gemma-s-s-ul2"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-t5gemma-s-s-ul2"},{"id":"translategemma-4b-it","name":"translategemma-4b-it","hf":"google/translategemma-4b-it","org":"google","family":"gemma","series":"translategemma","task":"translate","pipeline":"image-text-to-text","tags":[],"released":"2026-01-12","updated":"2026-01-28","gated":true,"params":{"total":4.3,"active":null,"src":"safetensors","q":null,"stTotal":4.3},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":8.6,"t":10},"fp8":{"w":4.57,"t":5.5},"q4":{"w":2.61,"t":3.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.6,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"translategemma:4b","url":"https://ollama.com/library/translategemma"}],"variants":[{"id":"google/translategemma-4b-it","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/translategemma-4b-it","u":"https://huggingface.co/google/translategemma-4b-it"},{"t":"Ollama library · translategemma","u":"https://ollama.com/library/translategemma"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-translategemma-4b-it"},{"id":"translategemma-12b-it","name":"translategemma-12b-it","hf":"google/translategemma-12b-it","org":"google","family":"gemma","series":"translategemma","task":"translate","pipeline":"image-text-to-text","tags":[],"released":"2026-01-12","updated":"2026-01-28","gated":true,"params":{"total":12.187,"active":null,"src":"safetensors","q":null,"stTotal":12.187},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":24.37,"t":27.3},"fp8":{"w":12.95,"t":14.7},"q4":{"w":7.39,"t":8.6}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24.37,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"translategemma:12b","url":"https://ollama.com/library/translategemma"}],"variants":[{"id":"google/translategemma-12b-it","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/translategemma-12b-it","u":"https://huggingface.co/google/translategemma-12b-it"},{"t":"Ollama library · translategemma","u":"https://ollama.com/library/translategemma"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-translategemma-12b-it"},{"id":"translategemma-27b-it","name":"translategemma-27b-it","hf":"google/translategemma-27b-it","org":"google","family":"gemma","series":"translategemma","task":"translate","pipeline":"image-text-to-text","tags":[],"released":"2026-01-12","updated":"2026-01-28","gated":true,"params":{"total":27.432,"active":null,"src":"safetensors","q":null,"stTotal":27.432},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":54.86,"t":60.9},"fp8":{"w":29.15,"t":32.6},"q4":{"w":16.63,"t":18.8}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":54.86,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"translategemma:27b","url":"https://ollama.com/library/translategemma"}],"variants":[{"id":"google/translategemma-27b-it","kind":"Instruct"}],"sources":[{"t":"Hugging Face · google/translategemma-27b-it","u":"https://huggingface.co/google/translategemma-27b-it"},{"t":"Ollama library · translategemma","u":"https://ollama.com/library/translategemma"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-translategemma-27b-it"},{"id":"vaultgemma-1b","name":"vaultgemma-1b","hf":"google/vaultgemma-1b","org":"google","family":"gemma","series":"vaultgemma","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-05","updated":"2025-09-12","gated":true,"params":{"total":1.039,"active":null,"src":"safetensors","q":null,"stTotal":1.039},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":2.08,"t":2.8},"fp8":{"w":1.1,"t":1.7},"q4":{"w":0.63,"t":1.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.08,"native":"BF16","license":{"id":"gemma","name":"Gemma Terms of Use","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"google/vaultgemma-1b","kind":"main"}],"sources":[{"t":"Hugging Face · google/vaultgemma-1b","u":"https://huggingface.co/google/vaultgemma-1b"}],"page":"https://aimap.page/en/models/compute/open-models/family/gemma/#m-vaultgemma-1b"},{"id":"autoglm-phone-9b","name":"AutoGLM-Phone-9B","hf":"zai-org/AutoGLM-Phone-9B","org":"zai-org","family":"glm","series":"AutoGLM-Phone","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-12-08","updated":"2026-01-07","gated":false,"params":{"total":9,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":65536,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.34,"32768":1.34},"mem":{"bf16":{"w":18,"t":20.6},"fp8":{"w":9.56,"t":11.4},"q4":{"w":5.46,"t":6.8}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":20.59,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/AutoGLM-Phone-9B","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/AutoGLM-Phone-9B","u":"https://huggingface.co/zai-org/AutoGLM-Phone-9B"},{"t":"config.json","u":"https://huggingface.co/zai-org/AutoGLM-Phone-9B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-autoglm-phone-9b"},{"id":"cogvideox-2b","name":"CogVideoX-2b","hf":"zai-org/CogVideoX-2b","org":"zai-org","family":"glm","series":"CogVideoX","task":"video","pipeline":"text-to-video","tags":[],"released":"2024-08-05","updated":"2024-11-23","gated":false,"params":{"total":1.694,"active":null,"src":"safetensors","q":null,"stTotal":1.694},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":3.39,"t":4.2},"fp8":{"w":1.8,"t":2.5},"q4":{"w":1.03,"t":1.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":13.77,"native":"F16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/zai-org/CogVideoX-2b/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"zai-org/CogVideoX-2b","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/CogVideoX-2b","u":"https://huggingface.co/zai-org/CogVideoX-2b"},{"t":"License","u":"https://huggingface.co/zai-org/CogVideoX-2b/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-cogvideox-2b"},{"id":"cogvideox-5b","name":"CogVideoX-5b","hf":"zai-org/CogVideoX-5b","org":"zai-org","family":"glm","series":"CogVideoX","task":"video","pipeline":"text-to-video","tags":[],"released":"2024-08-17","updated":"2024-11-23","gated":false,"params":{"total":5.57,"active":null,"src":"safetensors","q":null,"stTotal":5.57},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":11.14,"t":12.8},"fp8":{"w":5.92,"t":7},"q4":{"w":3.38,"t":4.2}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":21.53,"native":"BF16","license":{"id":"other","name":"other","link":"https://huggingface.co/THUDM/CogVideoX-5b/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"zai-org/CogVideoX-5b","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/CogVideoX-5b","u":"https://huggingface.co/zai-org/CogVideoX-5b"},{"t":"License","u":"https://huggingface.co/THUDM/CogVideoX-5b/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-cogvideox-5b"},{"id":"cogvideox-5b-i2v","name":"CogVideoX-5b-I2V","hf":"zai-org/CogVideoX-5b-I2V","org":"zai-org","family":"glm","series":"CogVideoX-I2V","task":"video","pipeline":"image-to-video","tags":[],"released":"2024-09-16","updated":"2024-11-23","gated":false,"params":{"total":5.625,"active":null,"src":"safetensors","q":null,"stTotal":5.625},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":11.25,"t":12.9},"fp8":{"w":5.98,"t":7.1},"q4":{"w":3.41,"t":4.3}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":21.64,"native":"BF16","license":{"id":"other","name":"other","link":"https://huggingface.co/THUDM/CogVideoX-5b-I2V/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"zai-org/CogVideoX-5b-I2V","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/CogVideoX-5b-I2V","u":"https://huggingface.co/zai-org/CogVideoX-5b-I2V"},{"t":"License","u":"https://huggingface.co/THUDM/CogVideoX-5b-I2V/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-cogvideox-5b-i2v"},{"id":"cogvideox1-5-5b-i2v","name":"CogVideoX1.5-5B-I2V","hf":"zai-org/CogVideoX1.5-5B-I2V","org":"zai-org","family":"glm","series":"CogVideoX1.5-I2V","task":"video","pipeline":"image-to-video","tags":[],"released":"2024-11-02","updated":"2025-03-18","gated":false,"params":{"total":5.572,"active":null,"src":"safetensors","q":null,"stTotal":5.572},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":11.14,"t":12.8},"fp8":{"w":5.92,"t":7},"q4":{"w":3.38,"t":4.2}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":31.05,"native":"BF16","license":{"id":"other","name":"other","link":"https://huggingface.co/THUDM/CogVideoX-5b-I2V/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"zai-org/CogVideoX1.5-5B-I2V","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/CogVideoX1.5-5B-I2V","u":"https://huggingface.co/zai-org/CogVideoX1.5-5B-I2V"},{"t":"License","u":"https://huggingface.co/THUDM/CogVideoX-5b-I2V/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-cogvideox1-5-5b-i2v"},{"id":"cogview4-6b","name":"CogView4-6B","hf":"zai-org/CogView4-6B","org":"zai-org","family":"glm","series":"CogView4","task":"image","pipeline":"text-to-image","tags":[],"released":"2025-03-03","updated":"2025-03-11","gated":false,"params":{"total":6.369,"active":null,"src":"safetensors","q":null,"stTotal":6.369},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":12.74,"t":14.5},"fp8":{"w":6.77,"t":7.9},"q4":{"w":3.86,"t":4.7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":31.11,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/zai-org/CogView4-6B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"zai-org/CogView4-6B","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/CogView4-6B","u":"https://huggingface.co/zai-org/CogView4-6B"},{"t":"License","u":"https://huggingface.co/zai-org/CogView4-6B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-cogview4-6b"},{"id":"glm-4-9b-0414","name":"GLM-4-9B-0414","hf":"zai-org/GLM-4-9B-0414","org":"zai-org","family":"glm","series":"GLM-4","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-07","updated":"2025-04-14","gated":false,"params":{"total":9.4,"active":null,"src":"safetensors","q":null,"stTotal":9.4},"moe":false,"ctx":32768,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.34,"32768":1.34},"mem":{"bf16":{"w":18.8,"t":21.5},"fp8":{"w":9.99,"t":11.8},"q4":{"w":5.7,"t":7.1}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":18.8,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/zai-org/GLM-4-9B-0414/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-4-9B-0414","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/GLM-4-9B-0414","u":"https://huggingface.co/zai-org/GLM-4-9B-0414"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-4-9B-0414/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/zai-org/GLM-4-9B-0414/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-4-9b-0414"},{"id":"glm-4-32b-0414","name":"GLM-4-32B-0414","hf":"zai-org/GLM-4-32B-0414","org":"zai-org","family":"glm","series":"GLM-4","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-07","updated":"2025-05-01","gated":false,"params":{"total":32.566,"active":null,"src":"safetensors","q":null,"stTotal":32.566},"moe":false,"ctx":32768,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.51,"32768":2.05},"mem":{"bf16":{"w":65.13,"t":72.7},"fp8":{"w":34.6,"t":39.1},"q4":{"w":19.74,"t":22.7}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":65.13,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/zai-org/GLM-4-32B-0414/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-4-32B-0414","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/GLM-4-32B-0414","u":"https://huggingface.co/zai-org/GLM-4-32B-0414"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-4-32B-0414/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/zai-org/GLM-4-32B-0414/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-4-32b-0414"},{"id":"glm-4-1v-9b-thinking","name":"GLM-4.1V-9B-Thinking","hf":"zai-org/GLM-4.1V-9B-Thinking","org":"zai-org","family":"glm","series":"GLM-4.1V-Thinking","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-06-28","updated":"2026-07-22","gated":false,"params":{"total":10.293,"active":null,"src":"safetensors","q":null,"stTotal":10.293},"moe":false,"ctx":65536,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.34,"32768":1.34},"mem":{"bf16":{"w":20.59,"t":23.5},"fp8":{"w":10.94,"t":12.9},"q4":{"w":6.24,"t":7.7}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":20.59,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-4.1V-9B-Thinking","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/GLM-4.1V-9B-Thinking","u":"https://huggingface.co/zai-org/GLM-4.1V-9B-Thinking"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-4.1V-9B-Thinking/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-4-1v-9b-thinking"},{"id":"glm-4-5","name":"GLM-4.5","hf":"zai-org/GLM-4.5","org":"zai-org","family":"glm","series":"GLM-4.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-20","updated":"2025-08-11","gated":false,"params":{"total":355,"active":32,"src":"card","q":"GLM-4.5 has 355 billion total parameters with 32 billion active parameters","stTotal":358.338},"moe":true,"ctx":131072,"arch":{"L":92,"attn":92,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":3.09,"32768":12.35,"131072":49.39},"mem":{"bf16":{"w":710,"t":784.6},"fp8":{"w":377.19,"t":418.5},"q4":{"w":215.22,"t":240.3}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":716.68,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-4.5","kind":"main"},{"id":"zai-org/GLM-4.5-FP8","kind":"FP8"},{"id":"zai-org/GLM-4.5-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · zai-org/GLM-4.5","u":"https://huggingface.co/zai-org/GLM-4.5"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-4.5/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/glm-4-5/"},{"id":"glm-4-5-air","name":"GLM-4.5-Air","hf":"zai-org/GLM-4.5-Air","org":"zai-org","family":"glm","series":"GLM-4.5-Air","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-20","updated":"2025-08-11","gated":false,"params":{"total":106,"active":12,"src":"card","q":"GLM-4.5-Air … 106 billion total parameters and 12 billion active parameters","stTotal":110.469},"moe":true,"ctx":131072,"arch":{"L":46,"attn":46,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.54,"32768":6.17,"131072":24.7},"mem":{"bf16":{"w":212,"t":235.2},"fp8":{"w":112.62,"t":125.9},"q4":{"w":64.26,"t":72.7}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":220.94,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-4.5-Air","kind":"main"},{"id":"zai-org/GLM-4.5-Air-FP8","kind":"FP8"},{"id":"zai-org/GLM-4.5-Air-Base","kind":"Base"},{"id":"zai-org/GLM-4.5V-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · zai-org/GLM-4.5-Air","u":"https://huggingface.co/zai-org/GLM-4.5-Air"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-4.5-Air/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/glm-4-5-air/"},{"id":"glm-4-5v","name":"GLM-4.5V","hf":"zai-org/GLM-4.5V","org":"zai-org","family":"glm","series":"GLM-4.5V","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-08-10","updated":"2025-10-25","gated":false,"params":{"total":107.711,"active":null,"src":"safetensors","q":null,"stTotal":107.711},"moe":true,"ctx":65536,"arch":{"L":46,"attn":46,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.54,"32768":6.17},"mem":{"bf16":{"w":215.42,"t":239},"fp8":{"w":114.44,"t":127.9},"q4":{"w":65.3,"t":73.9}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":215.42,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-4.5V","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/GLM-4.5V","u":"https://huggingface.co/zai-org/GLM-4.5V"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-4.5V/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/glm-4-5v/"},{"id":"glm-4-6","name":"GLM-4.6","hf":"zai-org/GLM-4.6","org":"zai-org","family":"glm","series":"GLM-4.6","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-29","updated":"2025-09-30","gated":false,"params":{"total":356.786,"active":null,"src":"safetensors","q":null,"stTotal":356.786},"moe":true,"ctx":202752,"arch":{"L":92,"attn":92,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":3.09,"32768":12.35,"131072":49.39},"mem":{"bf16":{"w":713.57,"t":788.5},"fp8":{"w":379.09,"t":420.6},"q4":{"w":216.3,"t":241.5}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":713.58,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-4.6","kind":"main"},{"id":"zai-org/GLM-4.6-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · zai-org/GLM-4.6","u":"https://huggingface.co/zai-org/GLM-4.6"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-4.6/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/glm-4-6/"},{"id":"glm-4-6v","name":"GLM-4.6V","hf":"zai-org/GLM-4.6V","org":"zai-org","family":"glm","series":"GLM-4.6V","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-12-07","updated":"2025-12-09","gated":false,"params":{"total":107.711,"active":null,"src":"safetensors","q":null,"stTotal":107.711},"moe":true,"ctx":131072,"arch":{"L":46,"attn":46,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.54,"32768":6.17,"131072":24.7},"mem":{"bf16":{"w":215.42,"t":239},"fp8":{"w":114.44,"t":127.9},"q4":{"w":65.3,"t":73.9}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":215.42,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-4.6V","kind":"main"},{"id":"zai-org/GLM-4.6V-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · zai-org/GLM-4.6V","u":"https://huggingface.co/zai-org/GLM-4.6V"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-4.6V/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/glm-4-6v/"},{"id":"glm-4-6v-flash","name":"GLM-4.6V-Flash","hf":"zai-org/GLM-4.6V-Flash","org":"zai-org","family":"glm","series":"GLM-4.6V-Flash","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-12-07","updated":"2025-12-09","gated":false,"params":{"total":10.293,"active":null,"src":"safetensors","q":null,"stTotal":10.293},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.34,"32768":1.34,"131072":5.37},"mem":{"bf16":{"w":20.59,"t":23.5},"fp8":{"w":10.94,"t":12.9},"q4":{"w":6.24,"t":7.7}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":20.59,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-4.6V-Flash","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/GLM-4.6V-Flash","u":"https://huggingface.co/zai-org/GLM-4.6V-Flash"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-4.6V-Flash/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-4-6v-flash"},{"id":"glm-4-7","name":"GLM-4.7","hf":"zai-org/GLM-4.7","org":"zai-org","family":"glm","series":"GLM-4.7","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-12-22","updated":"2026-01-29","gated":false,"params":{"total":358.338,"active":null,"src":"safetensors","q":null,"stTotal":358.338},"moe":true,"ctx":202752,"arch":{"L":92,"attn":92,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":3.09,"32768":12.35,"131072":49.39},"mem":{"bf16":{"w":716.68,"t":791.9},"fp8":{"w":380.73,"t":422.4},"q4":{"w":217.24,"t":242.6}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":716.68,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-4.7","kind":"main"},{"id":"zai-org/GLM-4.7-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · zai-org/GLM-4.7","u":"https://huggingface.co/zai-org/GLM-4.7"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-4.7/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/glm-4-7/"},{"id":"glm-4-7-flash","name":"GLM-4.7-Flash","hf":"zai-org/GLM-4.7-Flash","org":"zai-org","family":"glm","series":"GLM-4.7-Flash","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-01-19","updated":"2026-01-29","gated":false,"params":{"total":31.221,"active":3,"src":"safetensors","q":"GLM-4.7-Flash is a 30B-A3B MoE model.","stTotal":31.221},"moe":true,"ctx":202752,"arch":{"L":47,"attn":47,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.44,"32768":1.77,"131072":7.1},"mem":{"bf16":{"w":62.44,"t":69.6},"fp8":{"w":33.17,"t":37.4},"q4":{"w":18.93,"t":21.8}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":62.44,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"glm-4.7-flash","url":"https://ollama.com/library/glm-4.7-flash"}],"variants":[{"id":"zai-org/GLM-4.7-Flash","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/GLM-4.7-Flash","u":"https://huggingface.co/zai-org/GLM-4.7-Flash"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-4.7-Flash/blob/main/config.json"},{"t":"Ollama library · glm-4.7-flash","u":"https://ollama.com/library/glm-4.7-flash"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-4-7-flash"},{"id":"glm-5","name":"GLM-5","hf":"zai-org/GLM-5","org":"zai-org","family":"glm","series":"GLM-5","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-02-11","updated":"2026-08-11","gated":false,"params":{"total":744,"active":40,"src":"card","q":"GLM-5 scales from 355B parameters (32B active) to 744B parameters (40B active)","stTotal":753.864},"moe":true,"ctx":202752,"arch":{"L":78,"attn":78,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.74,"32768":2.94,"131072":11.78},"mem":{"bf16":{"w":1488,"t":1638},"fp8":{"w":790.5,"t":870.8},"q4":{"w":451.05,"t":497.4}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1507.74,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"zai-org/GLM-5","kind":"main"},{"id":"zai-org/GLM-5-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · zai-org/GLM-5","u":"https://huggingface.co/zai-org/GLM-5"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-5/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/glm-5/"},{"id":"glm-5-1","name":"GLM-5.1","hf":"zai-org/GLM-5.1","org":"zai-org","family":"glm","series":"GLM-5.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-03","updated":"2026-05-13","gated":false,"params":{"total":753.864,"active":null,"src":"safetensors","q":null,"stTotal":753.864},"moe":true,"ctx":202752,"arch":{"L":78,"attn":78,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.74,"32768":2.94,"131072":11.78},"mem":{"bf16":{"w":1507.73,"t":1659.7},"fp8":{"w":800.98,"t":882.3},"q4":{"w":457.03,"t":504}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1507.74,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/zai-org/GLM-5.1/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"zai-org/GLM-5.1","kind":"main"},{"id":"zai-org/GLM-5.1-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · zai-org/GLM-5.1","u":"https://huggingface.co/zai-org/GLM-5.1"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-5.1/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/zai-org/GLM-5.1/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/glm-5-1/"},{"id":"glm-5-2","name":"GLM-5.2","hf":"zai-org/GLM-5.2","org":"zai-org","family":"glm","series":"GLM-5.2","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-06-16","updated":"2026-09-01","gated":false,"params":{"total":753.33,"active":null,"src":"safetensors","q":null,"stTotal":753.33},"moe":true,"ctx":1048576,"arch":{"L":78,"attn":78,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.74,"32768":2.94,"131072":11.78},"mem":{"bf16":{"w":1506.66,"t":1658.6},"fp8":{"w":800.41,"t":881.7},"q4":{"w":456.71,"t":503.6}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1506.67,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/zai-org/GLM-5.2/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"zai-org/GLM-5.2","kind":"main"},{"id":"zai-org/GLM-5.2-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · zai-org/GLM-5.2","u":"https://huggingface.co/zai-org/GLM-5.2"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-5.2/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/zai-org/GLM-5.2/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/glm-5-2/"},{"id":"glm-5-3","name":"GLM-5.3","hf":"zai-org/GLM-5.3","org":"zai-org","family":"glm","series":"GLM-5.3","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-08-25","updated":"2026-10-14","gated":false,"params":{"total":753.33,"active":null,"src":"safetensors","q":null,"stTotal":753.33},"moe":true,"ctx":1048576,"arch":{"L":78,"attn":78,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.74,"32768":2.94,"131072":11.78},"mem":{"bf16":{"w":1506.66,"t":1658.6},"fp8":{"w":800.41,"t":881.7},"q4":{"w":456.71,"t":503.6}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":755.63,"native":"F8_E4M3","license":{"id":"glm-5.3","name":"glm-5.3","link":"https://huggingface.co/zai-org/GLM-5.3/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"zai-org/GLM-5.3","kind":"main"},{"id":"zai-org/GLM-5.3-BF16","kind":"BF16"}],"sources":[{"t":"Hugging Face · zai-org/GLM-5.3","u":"https://huggingface.co/zai-org/GLM-5.3"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-5.3/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/zai-org/GLM-5.3/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/glm-5-3/"},{"id":"glm-5-3-flash","name":"GLM-5.3-Flash","hf":"zai-org/GLM-5.3-Flash","org":"zai-org","family":"glm","series":"GLM-5.3-Flash","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-08-25","updated":"2026-10-15","gated":false,"params":{"total":320,"active":18,"src":"card","q":"320B total parameters and just 18B active parameters","stTotal":321.323},"moe":true,"ctx":1048576,"arch":{"L":45,"attn":11,"slide":0,"win":null,"kvElems":512,"kvMethod":"mla+hybrid","exotic":[]},"kv":{"8192":0.09,"32768":0.37,"131072":1.48},"mem":{"bf16":{"w":640,"t":704.6},"fp8":{"w":340,"t":374.6},"q4":{"w":194,"t":214}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":328.34,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/zai-org/GLM-5.3-Flash/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"zai-org/GLM-5.3-Flash","kind":"main"},{"id":"zai-org/GLM-5.3-Flash-BF16","kind":"BF16"}],"sources":[{"t":"Hugging Face · zai-org/GLM-5.3-Flash","u":"https://huggingface.co/zai-org/GLM-5.3-Flash"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-5.3-Flash/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/zai-org/GLM-5.3-Flash/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/glm-5-3-flash/"},{"id":"glm-asr-nano-2512","name":"GLM-ASR-Nano-2512","hf":"zai-org/GLM-ASR-Nano-2512","org":"zai-org","family":"glm","series":"GLM-ASR-Nano","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-12-09","updated":"2026-04-07","gated":false,"params":{"total":2.258,"active":null,"src":"safetensors","q":null,"stTotal":2.258},"moe":false,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":4.52,"t":5.5},"fp8":{"w":2.4,"t":3.1},"q4":{"w":1.37,"t":2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.52,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-ASR-Nano-2512","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/GLM-ASR-Nano-2512","u":"https://huggingface.co/zai-org/GLM-ASR-Nano-2512"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-ASR-Nano-2512/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-asr-nano-2512"},{"id":"glm-image","name":"GLM-Image","hf":"zai-org/GLM-Image","org":"zai-org","family":"glm","series":"GLM-Image","task":"image","pipeline":"text-to-image","tags":[],"released":"2026-01-08","updated":"2026-01-15","gated":false,"params":{"total":6.927,"active":null,"src":"safetensors","q":null,"stTotal":6.927},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":13.85,"t":15.7},"fp8":{"w":7.36,"t":8.6},"q4":{"w":4.2,"t":5.1}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":35.77,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"zai-org/GLM-Image","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/GLM-Image","u":"https://huggingface.co/zai-org/GLM-Image"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-image"},{"id":"glm-ocr","name":"GLM-OCR","hf":"zai-org/GLM-OCR","org":"zai-org","family":"glm","series":"GLM-OCR","task":"vlm","pipeline":"image-to-text","tags":["ocr"],"released":"2026-01-30","updated":"2026-09-11","gated":false,"params":{"total":1.325,"active":null,"src":"safetensors","q":null,"stTotal":1.325},"moe":false,"ctx":131072,"arch":{"L":16,"attn":16,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54,"32768":2.15,"131072":8.59},"mem":{"bf16":{"w":2.65,"t":4},"fp8":{"w":1.41,"t":2.6},"q4":{"w":0.8,"t":1.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.65,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"glm-ocr","url":"https://ollama.com/library/glm-ocr"}],"variants":[{"id":"zai-org/GLM-OCR","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/GLM-OCR","u":"https://huggingface.co/zai-org/GLM-OCR"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-OCR/blob/main/config.json"},{"t":"Ollama library · glm-ocr","u":"https://ollama.com/library/glm-ocr"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-ocr"},{"id":"glm-z1-9b-0414","name":"GLM-Z1-9B-0414","hf":"zai-org/GLM-Z1-9B-0414","org":"zai-org","family":"glm","series":"GLM-Z1","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-08","updated":"2025-04-28","gated":false,"params":{"total":9.4,"active":null,"src":"safetensors","q":null,"stTotal":9.4},"moe":false,"ctx":32768,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.34,"32768":1.34},"mem":{"bf16":{"w":18.8,"t":21.5},"fp8":{"w":9.99,"t":11.8},"q4":{"w":5.7,"t":7.1}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":18.8,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/zai-org/GLM-Z1-9B-0414/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-Z1-9B-0414","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/GLM-Z1-9B-0414","u":"https://huggingface.co/zai-org/GLM-Z1-9B-0414"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-Z1-9B-0414/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/zai-org/GLM-Z1-9B-0414/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-z1-9b-0414"},{"id":"glm-z1-32b-0414","name":"GLM-Z1-32B-0414","hf":"zai-org/GLM-Z1-32B-0414","org":"zai-org","family":"glm","series":"GLM-Z1","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-08","updated":"2025-04-28","gated":false,"params":{"total":32.566,"active":null,"src":"safetensors","q":null,"stTotal":32.566},"moe":false,"ctx":32768,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.51,"32768":2.05},"mem":{"bf16":{"w":65.13,"t":72.7},"fp8":{"w":34.6,"t":39.1},"q4":{"w":19.74,"t":22.7}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":65.13,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/zai-org/GLM-Z1-32B-0414/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/GLM-Z1-32B-0414","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/GLM-Z1-32B-0414","u":"https://huggingface.co/zai-org/GLM-Z1-32B-0414"},{"t":"config.json","u":"https://huggingface.co/zai-org/GLM-Z1-32B-0414/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/zai-org/GLM-Z1-32B-0414/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-z1-32b-0414"},{"id":"scail-2","name":"SCAIL-2","hf":"zai-org/SCAIL-2","org":"zai-org","family":"glm","series":"SCAIL-2","task":"video","pipeline":"image-to-video","tags":[],"released":"2026-06-09","updated":"2026-07-15","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":82.44,"native":null,"license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"zai-org/SCAIL-2","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/SCAIL-2","u":"https://huggingface.co/zai-org/SCAIL-2"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-scail-2"},{"id":"codegeex4-all-9b","name":"codegeex4-all-9b","hf":"zai-org/codegeex4-all-9b","org":"zai-org","family":"glm","series":"codegeex4-all","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-07-05","updated":"2024-07-18","gated":false,"params":{"total":9.4,"active":null,"src":"safetensors","q":null,"stTotal":9.4},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":5.37,"32768":21.47,"131072":85.9},"mem":{"bf16":{"w":18.8,"t":26.6},"fp8":{"w":9.99,"t":16.9},"q4":{"w":5.7,"t":12.1}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":18.8,"native":"BF16","license":{"id":"codegeex4","name":"codegeex4","link":"https://huggingface.co/THUDM/codegeex4-all-9b/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"zai-org/codegeex4-all-9b","kind":"main"},{"id":"zai-org/codegeex4-all-9b-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · zai-org/codegeex4-all-9b","u":"https://huggingface.co/zai-org/codegeex4-all-9b"},{"t":"config.json","u":"https://huggingface.co/zai-org/codegeex4-all-9b/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/THUDM/codegeex4-all-9b/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-codegeex4-all-9b"},{"id":"cogvlm2-llama3-chat-19b","name":"cogvlm2-llama3-chat-19B","hf":"zai-org/cogvlm2-llama3-chat-19B","org":"zai-org","family":"glm","series":"cogvlm2-llama3","task":"vlm","pipeline":"text-generation","tags":[],"released":"2024-05-16","updated":"2024-09-03","gated":false,"params":{"total":19.503,"active":null,"src":"safetensors","q":null,"stTotal":19.503},"moe":false,"ctx":8192,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":4.29},"mem":{"bf16":{"w":39.01,"t":47.7},"fp8":{"w":20.72,"t":27.6},"q4":{"w":11.82,"t":17.8}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":39.01,"native":"BF16","license":{"id":"cogvlm2","name":"cogvlm2","link":"https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/cogvlm2-llama3-chat-19B","kind":"Instruct"},{"id":"zai-org/cogvlm2-llama3-chat-19B-int4","kind":"Instruct/INT4"}],"sources":[{"t":"Hugging Face · zai-org/cogvlm2-llama3-chat-19B","u":"https://huggingface.co/zai-org/cogvlm2-llama3-chat-19B"},{"t":"config.json","u":"https://huggingface.co/zai-org/cogvlm2-llama3-chat-19B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-cogvlm2-llama3-chat-19b"},{"id":"glm-4-9b-chat","name":"glm-4-9b-chat","hf":"zai-org/glm-4-9b-chat","org":"zai-org","family":"glm","series":"glm-4","task":"llm","pipeline":null,"tags":[],"released":"2024-06-04","updated":"2025-03-13","gated":false,"params":{"total":9.4,"active":null,"src":"safetensors","q":null,"stTotal":9.4},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":5.37,"32768":21.47,"131072":85.9},"mem":{"bf16":{"w":18.8,"t":26.6},"fp8":{"w":9.99,"t":16.9},"q4":{"w":5.7,"t":12.1}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":18.8,"native":"BF16","license":{"id":"glm-4","name":"glm-4","link":"https://huggingface.co/THUDM/glm-4-9b-chat/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"glm4:9b","url":"https://ollama.com/library/glm4"}],"variants":[{"id":"zai-org/glm-4-9b-chat","kind":"Instruct"},{"id":"zai-org/glm-4-9b","kind":"main"},{"id":"zai-org/glm-4-9b-chat-hf","kind":"Instruct/HF-transformers"},{"id":"zai-org/glm-4-9b-hf","kind":"HF-transformers"}],"sources":[{"t":"Hugging Face · zai-org/glm-4-9b-chat","u":"https://huggingface.co/zai-org/glm-4-9b-chat"},{"t":"config.json","u":"https://huggingface.co/zai-org/glm-4-9b-chat/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/THUDM/glm-4-9b-chat/blob/main/LICENSE"},{"t":"Ollama library · glm4","u":"https://ollama.com/library/glm4"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-4-9b-chat"},{"id":"glm-4-9b-chat-1m","name":"glm-4-9b-chat-1m","hf":"zai-org/glm-4-9b-chat-1m","org":"zai-org","family":"glm","series":"glm-4","task":"llm","pipeline":null,"tags":[],"released":"2024-06-04","updated":"2025-07-10","gated":false,"params":{"total":9.484,"active":null,"src":"safetensors","q":null,"stTotal":9.484},"moe":false,"ctx":1048576,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":5.37,"32768":21.47,"131072":85.9},"mem":{"bf16":{"w":18.97,"t":26.7},"fp8":{"w":10.08,"t":17},"q4":{"w":5.75,"t":12.2}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":18.97,"native":"BF16","license":{"id":"glm-4","name":"glm-4","link":"https://huggingface.co/THUDM/glm-4-9b-chat-1m/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/glm-4-9b-chat-1m","kind":"Instruct"}],"sources":[{"t":"Hugging Face · zai-org/glm-4-9b-chat-1m","u":"https://huggingface.co/zai-org/glm-4-9b-chat-1m"},{"t":"config.json","u":"https://huggingface.co/zai-org/glm-4-9b-chat-1m/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/THUDM/glm-4-9b-chat-1m/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-4-9b-chat-1m"},{"id":"glm-4v-9b","name":"glm-4v-9b","hf":"zai-org/glm-4v-9b","org":"zai-org","family":"glm","series":"glm-4v","task":"llm","pipeline":null,"tags":[],"released":"2024-06-04","updated":"2025-03-03","gated":false,"params":{"total":13.906,"active":null,"src":"safetensors","q":null,"stTotal":13.906},"moe":false,"ctx":8192,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":5.37},"mem":{"bf16":{"w":27.81,"t":36.5},"fp8":{"w":14.78,"t":22.1},"q4":{"w":8.43,"t":15.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":27.81,"native":"BF16","license":{"id":"glm-4","name":"glm-4","link":"https://huggingface.co/THUDM/glm-4v-9b/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"zai-org/glm-4v-9b","kind":"main"}],"sources":[{"t":"Hugging Face · zai-org/glm-4v-9b","u":"https://huggingface.co/zai-org/glm-4v-9b"},{"t":"config.json","u":"https://huggingface.co/zai-org/glm-4v-9b/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/THUDM/glm-4v-9b/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-4v-9b"},{"id":"glm-edge-1-5b-chat","name":"glm-edge-1.5b-chat","hf":"zai-org/glm-edge-1.5b-chat","org":"zai-org","family":"glm","series":"glm-edge","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-11-20","updated":"2024-11-28","gated":false,"params":{"total":1.593,"active":null,"src":"safetensors","q":null,"stTotal":1.593},"moe":false,"ctx":8192,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47},"mem":{"bf16":{"w":3.19,"t":4.5},"fp8":{"w":1.69,"t":2.8},"q4":{"w":0.97,"t":2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.19,"native":"BF16","license":{"id":"glm-4","name":"glm-4","link":"https://huggingface.co/zai-org/glm-edge-1.5b-chat/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"zai-org/glm-edge-1.5b-chat","kind":"Instruct"},{"id":"zai-org/glm-edge-1.5b-chat-gguf","kind":"Instruct/GGUF"}],"sources":[{"t":"Hugging Face · zai-org/glm-edge-1.5b-chat","u":"https://huggingface.co/zai-org/glm-edge-1.5b-chat"},{"t":"config.json","u":"https://huggingface.co/zai-org/glm-edge-1.5b-chat/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/zai-org/glm-edge-1.5b-chat/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-edge-1-5b-chat"},{"id":"glm-edge-4b-chat","name":"glm-edge-4b-chat","hf":"zai-org/glm-edge-4b-chat","org":"zai-org","family":"glm","series":"glm-edge","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-11-20","updated":"2024-11-28","gated":false,"params":{"total":4.328,"active":null,"src":"safetensors","q":null,"stTotal":4.328},"moe":false,"ctx":8192,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1536,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.01},"mem":{"bf16":{"w":8.66,"t":11},"fp8":{"w":4.6,"t":6.6},"q4":{"w":2.62,"t":4.4}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.66,"native":"BF16","license":{"id":"glm-4","name":"glm-4","link":"https://huggingface.co/zai-org/glm-edge-4b-chat/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"zai-org/glm-edge-4b-chat-gguf","kind":"Instruct/GGUF"},{"id":"zai-org/glm-edge-4b-chat","kind":"Instruct"}],"sources":[{"t":"Hugging Face · zai-org/glm-edge-4b-chat","u":"https://huggingface.co/zai-org/glm-edge-4b-chat"},{"t":"config.json","u":"https://huggingface.co/zai-org/glm-edge-4b-chat/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/zai-org/glm-edge-4b-chat/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/glm/#m-glm-edge-4b-chat"},{"id":"gpt-oss-20b","name":"gpt-oss-20b","hf":"openai/gpt-oss-20b","org":"openai","family":"gpt-oss","series":"gpt-oss","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-08-04","updated":"2025-08-26","gated":false,"params":{"total":21,"active":3.6,"src":"card","q":"21B parameters with 3.6B active parameters","stTotal":20.915},"moe":true,"ctx":131072,"arch":{"L":24,"attn":12,"slide":12,"win":128,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.2,"32768":0.81,"131072":3.22},"mem":{"bf16":{"w":42,"t":46.9},"fp8":{"w":22.31,"t":25.2},"q4":{"w":12.73,"t":14.7}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":13.76,"native":"U8","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/openai/gpt-oss-20b/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"lmstudio","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gpt-oss:20b","url":"https://ollama.com/library/gpt-oss"}],"variants":[{"id":"openai/gpt-oss-20b","kind":"main"}],"sources":[{"t":"Hugging Face · openai/gpt-oss-20b","u":"https://huggingface.co/openai/gpt-oss-20b"},{"t":"config.json","u":"https://huggingface.co/openai/gpt-oss-20b/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/openai/gpt-oss-20b/blob/main/LICENSE"},{"t":"Ollama library · gpt-oss","u":"https://ollama.com/library/gpt-oss"}],"page":"https://aimap.page/en/models/compute/open-models/family/gpt-oss/#m-gpt-oss-20b"},{"id":"gpt-oss-120b","name":"gpt-oss-120b","hf":"openai/gpt-oss-120b","org":"openai","family":"gpt-oss","series":"gpt-oss","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-08-04","updated":"2025-08-26","gated":false,"params":{"total":117,"active":5.1,"src":"card","q":"117B parameters with 5.1B active parameters","stTotal":116.829},"moe":true,"ctx":131072,"arch":{"L":36,"attn":18,"slide":18,"win":128,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.31,"32768":1.21,"131072":4.84},"mem":{"bf16":{"w":234,"t":258.2},"fp8":{"w":124.31,"t":137.6},"q4":{"w":70.93,"t":78.8}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":65.25,"native":"U8","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/openai/gpt-oss-120b/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"lmstudio","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gpt-oss:120b","url":"https://ollama.com/library/gpt-oss"}],"variants":[{"id":"openai/gpt-oss-120b","kind":"main"}],"sources":[{"t":"Hugging Face · openai/gpt-oss-120b","u":"https://huggingface.co/openai/gpt-oss-120b"},{"t":"config.json","u":"https://huggingface.co/openai/gpt-oss-120b/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/openai/gpt-oss-120b/blob/main/LICENSE"},{"t":"Ollama library · gpt-oss","u":"https://ollama.com/library/gpt-oss"}],"page":"https://aimap.page/en/models/compute/open-models/gpt-oss-120b/"},{"id":"gpt-oss-safeguard-20b","name":"gpt-oss-safeguard-20b","hf":"openai/gpt-oss-safeguard-20b","org":"openai","family":"gpt-oss","series":"gpt-oss-safeguard","task":"guard","pipeline":"text-generation","tags":[],"released":"2025-09-18","updated":"2026-01-14","gated":false,"params":{"total":21,"active":3.6,"src":"card","q":"21B parameters with 3.6B active parameters","stTotal":21.512},"moe":true,"ctx":131072,"arch":{"L":24,"attn":12,"slide":12,"win":128,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.2,"32768":0.81,"131072":3.22},"mem":{"bf16":{"w":42,"t":46.9},"fp8":{"w":22.31,"t":25.2},"q4":{"w":12.73,"t":14.7}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":13.76,"native":"U8","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/openai/gpt-oss-safeguard-20b/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gpt-oss-safeguard:20b","url":"https://ollama.com/library/gpt-oss-safeguard"}],"variants":[{"id":"openai/gpt-oss-safeguard-20b","kind":"main"}],"sources":[{"t":"Hugging Face · openai/gpt-oss-safeguard-20b","u":"https://huggingface.co/openai/gpt-oss-safeguard-20b"},{"t":"config.json","u":"https://huggingface.co/openai/gpt-oss-safeguard-20b/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/openai/gpt-oss-safeguard-20b/blob/main/LICENSE"},{"t":"Ollama library · gpt-oss-safeguard","u":"https://ollama.com/library/gpt-oss-safeguard"}],"page":"https://aimap.page/en/models/compute/open-models/family/gpt-oss/#m-gpt-oss-safeguard-20b"},{"id":"gpt-oss-safeguard-120b","name":"gpt-oss-safeguard-120b","hf":"openai/gpt-oss-safeguard-120b","org":"openai","family":"gpt-oss","series":"gpt-oss-safeguard","task":"guard","pipeline":"text-generation","tags":[],"released":"2025-09-18","updated":"2025-10-29","gated":false,"params":{"total":117,"active":5.1,"src":"card","q":"117B parameters with 5.1B active parameters","stTotal":116.829},"moe":true,"ctx":131072,"arch":{"L":36,"attn":18,"slide":18,"win":128,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.31,"32768":1.21,"131072":4.84},"mem":{"bf16":{"w":234,"t":258.2},"fp8":{"w":124.31,"t":137.6},"q4":{"w":70.93,"t":78.8}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":65.25,"native":"U8","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/openai/gpt-oss-safeguard-120b/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"gpt-oss-safeguard:120b","url":"https://ollama.com/library/gpt-oss-safeguard"}],"variants":[{"id":"openai/gpt-oss-safeguard-120b","kind":"main"}],"sources":[{"t":"Hugging Face · openai/gpt-oss-safeguard-120b","u":"https://huggingface.co/openai/gpt-oss-safeguard-120b"},{"t":"config.json","u":"https://huggingface.co/openai/gpt-oss-safeguard-120b/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/openai/gpt-oss-safeguard-120b/blob/main/LICENSE"},{"t":"Ollama library · gpt-oss-safeguard","u":"https://ollama.com/library/gpt-oss-safeguard"}],"page":"https://aimap.page/en/models/compute/open-models/gpt-oss-safeguard-120b/"},{"id":"ensemble-forecasting-with-ibm-granite-time-series","name":"ensemble-forecasting-with-ibm-granite-time-series","hf":"ibm-granite/ensemble-forecasting-with-ibm-granite-time-series","org":"ibm-granite","family":"granite","series":"ensemble-forecasting-with-ibm-granite-time-series","task":"llm","pipeline":null,"tags":[],"released":"2026-10-01","updated":"2026-10-01","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":null,"native":null,"license":{"id":null,"name":null,"link":null,"cls":"unknown"},"runtimes":[],"variants":[{"id":"ibm-granite/ensemble-forecasting-with-ibm-granite-time-series","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/ensemble-forecasting-with-ibm-granite-time-series","u":"https://huggingface.co/ibm-granite/ensemble-forecasting-with-ibm-granite-time-series"}],"page":"https://aimap.page/en/models/compute/open-models/ensemble-forecasting-with-ibm-granite-time-series/"},{"id":"granite-3-0-2b-instruct","name":"granite-3.0-2b-instruct","hf":"ibm-granite/granite-3.0-2b-instruct","org":"ibm-granite","family":"granite","series":"granite-3.0","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-10-02","updated":"2024-12-19","gated":false,"params":{"total":2.634,"active":null,"src":"safetensors","q":null,"stTotal":2.634},"moe":false,"ctx":4096,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67},"mem":{"bf16":{"w":5.27,"t":7},"fp8":{"w":2.8,"t":4.2},"q4":{"w":1.6,"t":2.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.27,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-3.0-2b-base","kind":"Base"},{"id":"ibm-granite/granite-3.0-2b-instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.0-2b-instruct","u":"https://huggingface.co/ibm-granite/granite-3.0-2b-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.0-2b-instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-0-2b-instruct"},{"id":"granite-3-0-8b-instruct","name":"granite-3.0-8b-instruct","hf":"ibm-granite/granite-3.0-8b-instruct","org":"ibm-granite","family":"granite","series":"granite-3.0","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-10-02","updated":"2024-12-19","gated":false,"params":{"total":8.171,"active":null,"src":"safetensors","q":null,"stTotal":8.171},"moe":false,"ctx":4096,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34},"mem":{"bf16":{"w":16.34,"t":19.8},"fp8":{"w":8.68,"t":11.4},"q4":{"w":4.95,"t":7.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":16.34,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-3.0-8b-instruct","kind":"Instruct"},{"id":"ibm-granite/granite-3.0-8b-base","kind":"Base"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.0-8b-instruct","u":"https://huggingface.co/ibm-granite/granite-3.0-8b-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.0-8b-instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-0-8b-instruct"},{"id":"granite-3-0-1b-a400m-instruct","name":"granite-3.0-1b-a400m-instruct","hf":"ibm-granite/granite-3.0-1b-a400m-instruct","org":"ibm-granite","family":"granite","series":"granite-3.0-a400m","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-10-03","updated":"2024-12-19","gated":false,"params":{"total":1.335,"active":0.4,"src":"safetensors","q":"# Active Parameters: 400M","stTotal":1.335},"moe":true,"ctx":4096,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.4},"mem":{"bf16":{"w":2.67,"t":3.8},"fp8":{"w":1.42,"t":2.5},"q4":{"w":0.81,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.67,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-3.0-1b-a400m-instruct","kind":"Instruct"},{"id":"ibm-granite/granite-3.0-1b-a400m-base","kind":"Base"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.0-1b-a400m-instruct","u":"https://huggingface.co/ibm-granite/granite-3.0-1b-a400m-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.0-1b-a400m-instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-0-1b-a400m-instruct"},{"id":"granite-3-0-3b-a800m-instruct","name":"granite-3.0-3b-a800m-instruct","hf":"ibm-granite/granite-3.0-3b-a800m-instruct","org":"ibm-granite","family":"granite","series":"granite-3.0-a800m","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-10-03","updated":"2024-12-19","gated":false,"params":{"total":3.374,"active":0.8,"src":"safetensors","q":"# Active Parameters: 800M","stTotal":3.374},"moe":true,"ctx":4096,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54},"mem":{"bf16":{"w":6.75,"t":8.5},"fp8":{"w":3.58,"t":5},"q4":{"w":2.05,"t":3.3}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.75,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-3.0-3b-a800m-instruct","kind":"Instruct"},{"id":"ibm-granite/granite-3.0-3b-a800m-base","kind":"Base"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.0-3b-a800m-instruct","u":"https://huggingface.co/ibm-granite/granite-3.0-3b-a800m-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.0-3b-a800m-instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-0-3b-a800m-instruct"},{"id":"granite-3-1-2b-instruct","name":"granite-3.1-2b-instruct","hf":"ibm-granite/granite-3.1-2b-instruct","org":"ibm-granite","family":"granite","series":"granite-3.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-12-06","updated":"2025-04-16","gated":false,"params":{"total":2.534,"active":null,"src":"safetensors","q":null,"stTotal":2.534},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":5.07,"t":6.7},"fp8":{"w":2.69,"t":4.1},"q4":{"w":1.54,"t":2.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.07,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-3.1-2b-instruct","kind":"Instruct"},{"id":"ibm-granite/granite-3.1-2b-base","kind":"Base"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.1-2b-instruct","u":"https://huggingface.co/ibm-granite/granite-3.1-2b-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.1-2b-instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-1-2b-instruct"},{"id":"granite-3-1-8b-instruct","name":"granite-3.1-8b-instruct","hf":"ibm-granite/granite-3.1-8b-instruct","org":"ibm-granite","family":"granite","series":"granite-3.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-12-06","updated":"2025-04-16","gated":false,"params":{"total":8.171,"active":null,"src":"safetensors","q":null,"stTotal":8.171},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":16.34,"t":19.8},"fp8":{"w":8.68,"t":11.4},"q4":{"w":4.95,"t":7.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":16.34,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-3.1-8b-instruct","kind":"Instruct"},{"id":"ibm-granite/granite-3.1-8b-base","kind":"Base"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.1-8b-instruct","u":"https://huggingface.co/ibm-granite/granite-3.1-8b-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.1-8b-instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-1-8b-instruct"},{"id":"granite-3-1-1b-a400m-instruct","name":"granite-3.1-1b-a400m-instruct","hf":"ibm-granite/granite-3.1-1b-a400m-instruct","org":"ibm-granite","family":"granite","series":"granite-3.1-a400m","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-12-06","updated":"2026-07-07","gated":false,"params":{"total":1.335,"active":null,"src":"safetensors","q":null,"stTotal":1.335},"moe":true,"ctx":131072,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.4,"32768":1.61,"131072":6.44},"mem":{"bf16":{"w":2.67,"t":3.8},"fp8":{"w":1.42,"t":2.5},"q4":{"w":0.81,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.67,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-3.1-1b-a400m-instruct","kind":"Instruct"},{"id":"ibm-granite/granite-3.1-1b-a400m-base","kind":"Base"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.1-1b-a400m-instruct","u":"https://huggingface.co/ibm-granite/granite-3.1-1b-a400m-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.1-1b-a400m-instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-1-1b-a400m-instruct"},{"id":"granite-3-1-3b-a800m-instruct","name":"granite-3.1-3b-a800m-instruct","hf":"ibm-granite/granite-3.1-3b-a800m-instruct","org":"ibm-granite","family":"granite","series":"granite-3.1-a800m","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-12-06","updated":"2025-01-31","gated":false,"params":{"total":3.299,"active":null,"src":"safetensors","q":null,"stTotal":3.299},"moe":true,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54,"32768":2.15,"131072":8.59},"mem":{"bf16":{"w":6.6,"t":8.3},"fp8":{"w":3.51,"t":4.9},"q4":{"w":2,"t":3.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.6,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-3.1-3b-a800m-instruct","kind":"Instruct"},{"id":"ibm-granite/granite-3.1-3b-a800m-base","kind":"Base"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.1-3b-a800m-instruct","u":"https://huggingface.co/ibm-granite/granite-3.1-3b-a800m-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.1-3b-a800m-instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-1-3b-a800m-instruct"},{"id":"granite-3-2-2b-instruct","name":"granite-3.2-2b-instruct","hf":"ibm-granite/granite-3.2-2b-instruct","org":"ibm-granite","family":"granite","series":"granite-3.2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-02-17","updated":"2025-04-17","gated":false,"params":{"total":2.534,"active":null,"src":"safetensors","q":null,"stTotal":2.534},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":5.07,"t":6.7},"fp8":{"w":2.69,"t":4.1},"q4":{"w":1.54,"t":2.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.07,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"granite3.2:2b","url":"https://ollama.com/library/granite3.2"}],"variants":[{"id":"ibm-granite/granite-3.2-2b-instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.2-2b-instruct","u":"https://huggingface.co/ibm-granite/granite-3.2-2b-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.2-2b-instruct/blob/main/config.json"},{"t":"Ollama library · granite3.2","u":"https://ollama.com/library/granite3.2"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-2-2b-instruct"},{"id":"granite-3-2-8b-instruct","name":"granite-3.2-8b-instruct","hf":"ibm-granite/granite-3.2-8b-instruct","org":"ibm-granite","family":"granite","series":"granite-3.2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-02-17","updated":"2025-04-17","gated":false,"params":{"total":8.171,"active":null,"src":"safetensors","q":null,"stTotal":8.171},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":16.34,"t":19.8},"fp8":{"w":8.68,"t":11.4},"q4":{"w":4.95,"t":7.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":16.34,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"granite3.2:8b","url":"https://ollama.com/library/granite3.2"}],"variants":[{"id":"ibm-granite/granite-3.2-8b-instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.2-8b-instruct","u":"https://huggingface.co/ibm-granite/granite-3.2-8b-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.2-8b-instruct/blob/main/config.json"},{"t":"Ollama library · granite3.2","u":"https://ollama.com/library/granite3.2"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-2-8b-instruct"},{"id":"granite-3-3-2b-instruct","name":"granite-3.3-2b-instruct","hf":"ibm-granite/granite-3.3-2b-instruct","org":"ibm-granite","family":"granite","series":"granite-3.3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-09","updated":"2025-05-08","gated":false,"params":{"total":2.534,"active":null,"src":"safetensors","q":null,"stTotal":2.534},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":5.07,"t":6.7},"fp8":{"w":2.69,"t":4.1},"q4":{"w":1.54,"t":2.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.07,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"granite3.3:2b","url":"https://ollama.com/library/granite3.3"}],"variants":[{"id":"ibm-granite/granite-3.3-2b-instruct","kind":"Instruct"},{"id":"ibm-granite/granite-3.3-2b-instruct-GGUF","kind":"Instruct/GGUF"},{"id":"ibm-granite/granite-3.3-2b-base","kind":"Base"},{"id":"ibm-granite/granite-3.3-2b-base-GGUF","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.3-2b-instruct","u":"https://huggingface.co/ibm-granite/granite-3.3-2b-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.3-2b-instruct/blob/main/config.json"},{"t":"Ollama library · granite3.3","u":"https://ollama.com/library/granite3.3"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-3-2b-instruct"},{"id":"granite-3-3-8b-instruct","name":"granite-3.3-8b-instruct","hf":"ibm-granite/granite-3.3-8b-instruct","org":"ibm-granite","family":"granite","series":"granite-3.3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-09","updated":"2025-05-12","gated":false,"params":{"total":8.171,"active":null,"src":"safetensors","q":null,"stTotal":8.171},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":16.34,"t":19.8},"fp8":{"w":8.68,"t":11.4},"q4":{"w":4.95,"t":7.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":16.34,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"granite3.3:8b","url":"https://ollama.com/library/granite3.3"}],"variants":[{"id":"ibm-granite/granite-3.3-8b-instruct","kind":"Instruct"},{"id":"ibm-granite/granite-3.3-8b-instruct-GGUF","kind":"Instruct/GGUF"},{"id":"ibm-granite/granite-3.3-8b-base","kind":"Base"},{"id":"ibm-granite/granite-3.3-8b-instruct-FP8","kind":"Instruct/FP8"},{"id":"ibm-granite/granite-3.3-8b-base-GGUF","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-3.3-8b-instruct","u":"https://huggingface.co/ibm-granite/granite-3.3-8b-instruct"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-3.3-8b-instruct/blob/main/config.json"},{"t":"Ollama library · granite3.3","u":"https://ollama.com/library/granite3.3"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-3-3-8b-instruct"},{"id":"granite-4-0-350m","name":"granite-4.0-350m","hf":"ibm-granite/granite-4.0-350m","org":"ibm-granite","family":"granite","series":"granite-4.0","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-10-07","updated":"2025-10-23","gated":false,"params":{"total":0.352,"active":null,"src":"safetensors","q":null,"stTotal":0.352},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.23,"32768":0.94},"mem":{"bf16":{"w":0.7,"t":1.5},"fp8":{"w":0.37,"t":1.1},"q4":{"w":0.21,"t":1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.7,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-4.0-350m","kind":"main"},{"id":"ibm-granite/granite-4.0-350m-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.0-350m-base","kind":"Base"},{"id":"ibm-granite/granite-4.0-350m-base-GGUF","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.0-350m","u":"https://huggingface.co/ibm-granite/granite-4.0-350m"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.0-350m/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-0-350m"},{"id":"granite-4-0-1b","name":"granite-4.0-1b","hf":"ibm-granite/granite-4.0-1b","org":"ibm-granite","family":"granite","series":"granite-4.0","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-10-07","updated":"2025-10-23","gated":false,"params":{"total":1.632,"active":null,"src":"safetensors","q":null,"stTotal":1.632},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":3.26,"t":4.8},"fp8":{"w":1.73,"t":3.1},"q4":{"w":0.99,"t":2.3}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.26,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-4.0-1b-base","kind":"Base"},{"id":"ibm-granite/granite-4.0-1b","kind":"main"},{"id":"ibm-granite/granite-4.0-1b-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.0-1b-base-GGUF","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.0-1b","u":"https://huggingface.co/ibm-granite/granite-4.0-1b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.0-1b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-0-1b"},{"id":"granite-4-0-h-350m","name":"granite-4.0-h-350m","hf":"ibm-granite/granite-4.0-h-350m","org":"ibm-granite","family":"granite","series":"granite-4.0-h","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-10-07","updated":"2025-10-23","gated":false,"params":{"total":0.34,"active":null,"src":"safetensors","q":null,"stTotal":0.34},"moe":false,"ctx":32768,"arch":{"L":32,"attn":4,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.03,"32768":0.13},"mem":{"bf16":{"w":0.68,"t":1.3},"fp8":{"w":0.36,"t":0.9},"q4":{"w":0.21,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.68,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-4.0-h-350m","kind":"main"},{"id":"ibm-granite/granite-4.0-h-350m-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.0-h-350m-base-GGUF","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.0-h-350m","u":"https://huggingface.co/ibm-granite/granite-4.0-h-350m"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.0-h-350m/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-0-h-350m"},{"id":"granite-4-0-h-1b","name":"granite-4.0-h-1b","hf":"ibm-granite/granite-4.0-h-1b","org":"ibm-granite","family":"granite","series":"granite-4.0-h","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-10-07","updated":"2025-10-23","gated":false,"params":{"total":1.462,"active":null,"src":"safetensors","q":null,"stTotal":1.462},"moe":false,"ctx":131072,"arch":{"L":40,"attn":4,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.07,"32768":0.27,"131072":1.07},"mem":{"bf16":{"w":2.92,"t":3.8},"fp8":{"w":1.55,"t":2.3},"q4":{"w":0.89,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.92,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-4.0-h-1b-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.0-h-1b","kind":"main"},{"id":"ibm-granite/granite-4.0-h-1b-base","kind":"Base"},{"id":"ibm-granite/granite-4.0-h-1b-base-GGUF","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.0-h-1b","u":"https://huggingface.co/ibm-granite/granite-4.0-h-1b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.0-h-1b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-0-h-1b"},{"id":"granite-4-0-h-micro","name":"granite-4.0-h-micro","hf":"ibm-granite/granite-4.0-h-micro","org":"ibm-granite","family":"granite","series":"granite-4.0-h-micro","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-16","updated":"2025-11-03","gated":false,"params":{"total":3.191,"active":null,"src":"safetensors","q":null,"stTotal":3.191},"moe":false,"ctx":131072,"arch":{"L":40,"attn":4,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.07,"32768":0.27,"131072":1.07},"mem":{"bf16":{"w":6.38,"t":7.6},"fp8":{"w":3.39,"t":4.3},"q4":{"w":1.93,"t":2.7}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.38,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-4.0-h-micro","kind":"main"},{"id":"ibm-granite/granite-4.0-h-micro-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.0-h-micro-base-GGUF","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.0-h-micro","u":"https://huggingface.co/ibm-granite/granite-4.0-h-micro"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.0-h-micro/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-0-h-micro"},{"id":"granite-4-0-h-small","name":"granite-4.0-h-small","hf":"ibm-granite/granite-4.0-h-small","org":"ibm-granite","family":"granite","series":"granite-4.0-h-small","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-16","updated":"2025-11-03","gated":false,"params":{"total":32.207,"active":null,"src":"safetensors","q":null,"stTotal":32.207},"moe":true,"ctx":131072,"arch":{"L":40,"attn":4,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.13,"32768":0.54,"131072":2.15},"mem":{"bf16":{"w":64.41,"t":71.5},"fp8":{"w":34.22,"t":38.3},"q4":{"w":19.53,"t":22.1}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":64.41,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-4.0-h-small","kind":"main"},{"id":"ibm-granite/granite-4.0-h-small-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.0-h-small-FP8","kind":"FP8"},{"id":"ibm-granite/granite-4.0-h-small-base-GGUF","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.0-h-small","u":"https://huggingface.co/ibm-granite/granite-4.0-h-small"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.0-h-small/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-0-h-small"},{"id":"granite-4-0-h-tiny","name":"granite-4.0-h-tiny","hf":"ibm-granite/granite-4.0-h-tiny","org":"ibm-granite","family":"granite","series":"granite-4.0-h-tiny","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-16","updated":"2025-11-03","gated":false,"params":{"total":6.939,"active":null,"src":"safetensors","q":null,"stTotal":6.939},"moe":true,"ctx":131072,"arch":{"L":40,"attn":4,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.07,"32768":0.27,"131072":1.07},"mem":{"bf16":{"w":13.88,"t":15.8},"fp8":{"w":7.37,"t":8.7},"q4":{"w":4.21,"t":5.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":13.88,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-4.0-h-tiny","kind":"main"},{"id":"ibm-granite/granite-4.0-h-tiny-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.0-h-tiny-base","kind":"Base"},{"id":"ibm-granite/granite-4.0-h-tiny-base-GGUF","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.0-h-tiny","u":"https://huggingface.co/ibm-granite/granite-4.0-h-tiny"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.0-h-tiny/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-0-h-tiny"},{"id":"granite-4-0-micro","name":"granite-4.0-micro","hf":"ibm-granite/granite-4.0-micro","org":"ibm-granite","family":"granite","series":"granite-4.0-micro","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-16","updated":"2025-11-03","gated":false,"params":{"total":3.403,"active":null,"src":"safetensors","q":null,"stTotal":3.403},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":6.81,"t":8.7},"fp8":{"w":3.62,"t":5.1},"q4":{"w":2.06,"t":3.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.81,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-4.0-micro","kind":"main"},{"id":"ibm-granite/granite-4.0-micro-GGUF","kind":"GGUF"},{"id":"ibm-granite/granitelib-rag-r1.0","kind":"main"},{"id":"ibm-granite/granite-4.0-micro-base","kind":"Base"},{"id":"ibm-granite/granite-4.0-micro-base-GGUF","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.0-micro","u":"https://huggingface.co/ibm-granite/granite-4.0-micro"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.0-micro/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-0-micro"},{"id":"granite-4-0-1b-speech","name":"granite-4.0-1b-speech","hf":"ibm-granite/granite-4.0-1b-speech","org":"ibm-granite","family":"granite","series":"granite-4.0-speech","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-02-27","updated":"2026-04-02","gated":false,"params":{"total":2.313,"active":null,"src":"safetensors","q":null,"stTotal":2.313},"moe":false,"ctx":4096,"arch":null,"kv":null,"mem":{"bf16":{"w":4.63,"t":5.6},"fp8":{"w":2.46,"t":3.2},"q4":{"w":1.4,"t":2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.63,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-4.0-1b-speech","kind":"main"},{"id":"ibm-granite/granite-4.0-1b-speech-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.0-1b-speech","u":"https://huggingface.co/ibm-granite/granite-4.0-1b-speech"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.0-1b-speech/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-0-1b-speech"},{"id":"granite-4-0-tiny-preview","name":"granite-4.0-tiny-preview","hf":"ibm-granite/granite-4.0-tiny-preview","org":"ibm-granite","family":"granite","series":"granite-4.0-tiny-preview","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-30","updated":"2025-11-03","gated":false,"params":{"total":6.672,"active":null,"src":"safetensors","q":null,"stTotal":6.672},"moe":true,"ctx":131072,"arch":{"L":40,"attn":4,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.07,"32768":0.27,"131072":1.07},"mem":{"bf16":{"w":13.34,"t":15.2},"fp8":{"w":7.09,"t":8.4},"q4":{"w":4.04,"t":5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":13.34,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-4.0-tiny-preview","kind":"main"},{"id":"ibm-granite/granite-4.0-tiny-preview-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.0-tiny-base-preview-GGUF","kind":"Base/GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.0-tiny-preview","u":"https://huggingface.co/ibm-granite/granite-4.0-tiny-preview"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.0-tiny-preview/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-0-tiny-preview"},{"id":"granite-4-0-3b-vision","name":"granite-4.0-3b-vision","hf":"ibm-granite/granite-4.0-3b-vision","org":"ibm-granite","family":"granite","series":"granite-4.0-vision","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-03-03","updated":"2026-04-30","gated":false,"params":{"total":3.997,"active":null,"src":"safetensors","q":null,"stTotal":3.997},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":7.99,"t":10},"fp8":{"w":4.25,"t":5.8},"q4":{"w":2.42,"t":3.8}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":9.45,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-4.0-3b-vision","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.0-3b-vision","u":"https://huggingface.co/ibm-granite/granite-4.0-3b-vision"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.0-3b-vision/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-0-3b-vision"},{"id":"granite-4-1-3b","name":"granite-4.1-3b","hf":"ibm-granite/granite-4.1-3b","org":"ibm-granite","family":"granite","series":"granite-4.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-06","updated":"2026-05-04","gated":false,"params":{"total":3.403,"active":null,"src":"safetensors","q":null,"stTotal":3.403},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":6.81,"t":8.7},"fp8":{"w":3.62,"t":5.1},"q4":{"w":2.06,"t":3.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.81,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"granite4.1:3b","url":"https://ollama.com/library/granite4.1"}],"variants":[{"id":"ibm-granite/granite-4.1-3b","kind":"main"},{"id":"ibm-granite/granite-4.1-3b-base","kind":"Base"},{"id":"ibm-granite/granite-4.1-3b-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.1-3b-fp8","kind":"FP8"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.1-3b","u":"https://huggingface.co/ibm-granite/granite-4.1-3b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.1-3b/blob/main/config.json"},{"t":"Ollama library · granite4.1","u":"https://ollama.com/library/granite4.1"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-1-3b"},{"id":"granite-4-1-8b","name":"granite-4.1-8b","hf":"ibm-granite/granite-4.1-8b","org":"ibm-granite","family":"granite","series":"granite-4.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-06","updated":"2026-05-04","gated":false,"params":{"total":8.792,"active":null,"src":"safetensors","q":null,"stTotal":8.792},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":17.58,"t":21.2},"fp8":{"w":9.34,"t":12.1},"q4":{"w":5.33,"t":7.7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":17.58,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"granite4.1:8b","url":"https://ollama.com/library/granite4.1"}],"variants":[{"id":"ibm-granite/granite-4.1-8b","kind":"main"},{"id":"ibm-granite/granite-4.1-8b-fp8","kind":"FP8"},{"id":"ibm-granite/granite-4.1-8b-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.1-8b-base","kind":"Base"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.1-8b","u":"https://huggingface.co/ibm-granite/granite-4.1-8b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.1-8b/blob/main/config.json"},{"t":"Ollama library · granite4.1","u":"https://ollama.com/library/granite4.1"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-1-8b"},{"id":"granite-4-1-30b","name":"granite-4.1-30b","hf":"ibm-granite/granite-4.1-30b","org":"ibm-granite","family":"granite","series":"granite-4.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-06","updated":"2026-05-04","gated":false,"params":{"total":28.866,"active":null,"src":"safetensors","q":null,"stTotal":28.866},"moe":false,"ctx":131072,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59,"131072":34.36},"mem":{"bf16":{"w":57.73,"t":66.2},"fp8":{"w":30.67,"t":36.4},"q4":{"w":17.5,"t":21.9}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":57.73,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"granite4.1:30b","url":"https://ollama.com/library/granite4.1"}],"variants":[{"id":"ibm-granite/granite-4.1-30b","kind":"main"},{"id":"ibm-granite/granite-4.1-30b-base","kind":"Base"},{"id":"ibm-granite/granite-4.1-30b-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.1-30b-fp8","kind":"FP8"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.1-30b","u":"https://huggingface.co/ibm-granite/granite-4.1-30b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.1-30b/blob/main/config.json"},{"t":"Ollama library · granite4.1","u":"https://ollama.com/library/granite4.1"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-1-30b"},{"id":"granite-4-2-3b","name":"granite-4.2-3b","hf":"ibm-granite/granite-4.2-3b","org":"ibm-granite","family":"granite","series":"granite-4.2","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-08-07","updated":"2026-10-20","gated":false,"params":{"total":3.66,"active":null,"src":"safetensors","q":null,"stTotal":3.66},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":7.32,"t":9.2},"fp8":{"w":3.89,"t":5.4},"q4":{"w":2.22,"t":3.6}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.32,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"},{"id":"ollama","via":"ollama-library","tag":"granite4.2:3b","url":"https://ollama.com/library/granite4.2"}],"variants":[{"id":"ibm-granite/granite-4.2-3b-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.2-3b","kind":"main"},{"id":"ibm-granite/granite-4.2-3b-fp8","kind":"FP8"},{"id":"ibm-granite/granite-4.2-3b-nvfp4","kind":"NVFP4"},{"id":"ibm-granite/granite-4.2-3b-mxfp4","kind":"MXFP4"},{"id":"ibm-granite/granite-4.2-3b-q4-mlx","kind":"MLX"},{"id":"ibm-granite/granite-4.2-3b-q8-mlx","kind":"MLX"},{"id":"ibm-granite/granite-4.2-3b-bf16-mlx","kind":"BF16/MLX"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.2-3b","u":"https://huggingface.co/ibm-granite/granite-4.2-3b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.2-3b/blob/main/config.json"},{"t":"Ollama library · granite4.2","u":"https://ollama.com/library/granite4.2"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-2-3b"},{"id":"granite-4-2-8b","name":"granite-4.2-8b","hf":"ibm-granite/granite-4.2-8b","org":"ibm-granite","family":"granite","series":"granite-4.2","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-08-07","updated":"2026-10-20","gated":false,"params":{"total":8.792,"active":null,"src":"safetensors","q":null,"stTotal":8.792},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":17.58,"t":21.2},"fp8":{"w":9.34,"t":12.1},"q4":{"w":5.33,"t":7.7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":17.58,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"},{"id":"ollama","via":"ollama-library","tag":"granite4.2:8b","url":"https://ollama.com/library/granite4.2"}],"variants":[{"id":"ibm-granite/granite-4.2-8b-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.2-8b","kind":"main"},{"id":"ibm-granite/granite-4.2-8b-fp8","kind":"FP8"},{"id":"ibm-granite/granite-4.2-8b-nvfp4","kind":"NVFP4"},{"id":"ibm-granite/granite-4.2-8b-mxfp4","kind":"MXFP4"},{"id":"ibm-granite/granite-4.2-8b-q4-mlx","kind":"MLX"},{"id":"ibm-granite/granite-4.2-8b-q8-mlx","kind":"MLX"},{"id":"ibm-granite/granite-4.2-8b-bf16-mlx","kind":"BF16/MLX"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.2-8b","u":"https://huggingface.co/ibm-granite/granite-4.2-8b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.2-8b/blob/main/config.json"},{"t":"Ollama library · granite4.2","u":"https://ollama.com/library/granite4.2"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-2-8b"},{"id":"granite-4-2-30b","name":"granite-4.2-30b","hf":"ibm-granite/granite-4.2-30b","org":"ibm-granite","family":"granite","series":"granite-4.2","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-08-07","updated":"2026-09-04","gated":false,"params":{"total":29.277,"active":null,"src":"safetensors","q":null,"stTotal":29.277},"moe":false,"ctx":131072,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59,"131072":34.36},"mem":{"bf16":{"w":58.55,"t":67.1},"fp8":{"w":31.11,"t":36.9},"q4":{"w":17.75,"t":22.2}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":58.55,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"},{"id":"ollama","via":"ollama-library","tag":"granite4.2:30b","url":"https://ollama.com/library/granite4.2"}],"variants":[{"id":"ibm-granite/granite-4.2-30b-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-4.2-30b","kind":"main"},{"id":"ibm-granite/granite-4.2-30b-nvfp4","kind":"NVFP4"},{"id":"ibm-granite/granite-4.2-30b-fp8","kind":"FP8"},{"id":"ibm-granite/granite-4.2-30b-mxfp4","kind":"MXFP4"},{"id":"ibm-granite/granite-4.2-30b-q4-mlx","kind":"MLX"},{"id":"ibm-granite/granite-4.2-30b-q8-mlx","kind":"MLX"},{"id":"ibm-granite/granite-4.2-30b-bf16-mlx","kind":"BF16/MLX"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-4.2-30b","u":"https://huggingface.co/ibm-granite/granite-4.2-30b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-4.2-30b/blob/main/config.json"},{"t":"Ollama library · granite4.2","u":"https://ollama.com/library/granite4.2"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-4-2-30b"},{"id":"granite-8b-code-instruct-128k","name":"granite-8b-code-instruct-128k","hf":"ibm-granite/granite-8b-code-instruct-128k","org":"ibm-granite","family":"granite","series":"granite-code-128k","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-07-12","updated":"2026-04-25","gated":false,"params":{"total":8.055,"active":null,"src":"safetensors","q":null,"stTotal":8.055},"moe":false,"ctx":128000,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":16.11,"t":19.4},"fp8":{"w":8.56,"t":11.1},"q4":{"w":4.88,"t":7.1}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.11,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-8b-code-instruct-128k","kind":"Instruct"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-8b-code-instruct-128k","u":"https://huggingface.co/ibm-granite/granite-8b-code-instruct-128k"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-8b-code-instruct-128k/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-8b-code-instruct-128k"},{"id":"granite-docling-258m","name":"granite-docling-258M","hf":"ibm-granite/granite-docling-258M","org":"ibm-granite","family":"granite","series":"granite-docling","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2025-05-19","updated":"2025-09-23","gated":false,"params":{"total":0.258,"active":null,"src":"safetensors","q":null,"stTotal":0.258},"moe":false,"ctx":8192,"arch":{"L":30,"attn":30,"slide":0,"win":null,"kvElems":384,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.19},"mem":{"bf16":{"w":0.52,"t":1.3},"fp8":{"w":0.27,"t":1},"q4":{"w":0.16,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.52,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-docling-258M","kind":"main"},{"id":"ibm-granite/granite-docling-258M-mlx","kind":"MLX"},{"id":"ibm-granite/granite-docling-258M-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-docling-258M","u":"https://huggingface.co/ibm-granite/granite-docling-258M"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-docling-258M/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-docling-258m"},{"id":"granite-embedding-30m-english","name":"granite-embedding-30m-english","hf":"ibm-granite/granite-embedding-30m-english","org":"ibm-granite","family":"granite","series":"granite-embedding-english","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2024-12-04","updated":"2025-08-22","gated":false,"params":{"total":0.03,"active":null,"src":"safetensors","q":null,"stTotal":0.03},"moe":false,"ctx":514,"arch":null,"kv":null,"mem":{"bf16":{"w":0.06,"t":0.6},"fp8":{"w":0.03,"t":0.5},"q4":{"w":0.02,"t":0.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.06,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-embedding-30m-english","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-embedding-30m-english","u":"https://huggingface.co/ibm-granite/granite-embedding-30m-english"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-embedding-30m-english/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-embedding-30m-english"},{"id":"granite-embedding-125m-english","name":"granite-embedding-125m-english","hf":"ibm-granite/granite-embedding-125m-english","org":"ibm-granite","family":"granite","series":"granite-embedding-english","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2024-12-04","updated":"2025-08-19","gated":false,"params":{"total":0.125,"active":null,"src":"safetensors","q":null,"stTotal":0.125},"moe":false,"ctx":514,"arch":null,"kv":null,"mem":{"bf16":{"w":0.25,"t":0.8},"fp8":{"w":0.13,"t":0.6},"q4":{"w":0.08,"t":0.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.25,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-embedding-125m-english","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-embedding-125m-english","u":"https://huggingface.co/ibm-granite/granite-embedding-125m-english"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-embedding-125m-english/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-embedding-125m-english"},{"id":"granite-embedding-english-r2","name":"granite-embedding-english-r2","hf":"ibm-granite/granite-embedding-english-r2","org":"ibm-granite","family":"granite","series":"granite-embedding-english-r2","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2025-07-17","updated":"2026-01-06","gated":false,"params":{"total":0.149,"active":null,"src":"safetensors","q":null,"stTotal":0.149},"moe":false,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":0.3,"t":0.8},"fp8":{"w":0.16,"t":0.7},"q4":{"w":0.09,"t":0.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.3,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-embedding-english-r2","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-embedding-english-r2","u":"https://huggingface.co/ibm-granite/granite-embedding-english-r2"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-embedding-english-r2/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-embedding-english-r2"},{"id":"granite-embedding-107m-multilingual","name":"granite-embedding-107m-multilingual","hf":"ibm-granite/granite-embedding-107m-multilingual","org":"ibm-granite","family":"granite","series":"granite-embedding-multilingual","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2024-12-04","updated":"2025-08-19","gated":false,"params":{"total":0.107,"active":null,"src":"safetensors","q":null,"stTotal":0.107},"moe":false,"ctx":514,"arch":null,"kv":null,"mem":{"bf16":{"w":0.21,"t":0.7},"fp8":{"w":0.11,"t":0.6},"q4":{"w":0.06,"t":0.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.21,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-embedding-107m-multilingual","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-embedding-107m-multilingual","u":"https://huggingface.co/ibm-granite/granite-embedding-107m-multilingual"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-embedding-107m-multilingual/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-embedding-107m-multilingual"},{"id":"granite-embedding-278m-multilingual","name":"granite-embedding-278m-multilingual","hf":"ibm-granite/granite-embedding-278m-multilingual","org":"ibm-granite","family":"granite","series":"granite-embedding-multilingual","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2024-12-04","updated":"2025-08-19","gated":false,"params":{"total":0.278,"active":null,"src":"safetensors","q":null,"stTotal":0.278},"moe":false,"ctx":514,"arch":null,"kv":null,"mem":{"bf16":{"w":0.56,"t":1.1},"fp8":{"w":0.3,"t":0.8},"q4":{"w":0.17,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.56,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-embedding-278m-multilingual","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-embedding-278m-multilingual","u":"https://huggingface.co/ibm-granite/granite-embedding-278m-multilingual"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-embedding-278m-multilingual/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-embedding-278m-multilingual"},{"id":"granite-embedding-97m-multilingual-r2","name":"granite-embedding-97m-multilingual-r2","hf":"ibm-granite/granite-embedding-97m-multilingual-r2","org":"ibm-granite","family":"granite","series":"granite-embedding-multilingual-r2","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-04-20","updated":"2026-05-18","gated":false,"params":{"total":0.097,"active":null,"src":"safetensors","q":null,"stTotal":0.097},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":0.19,"t":0.7},"fp8":{"w":0.1,"t":0.6},"q4":{"w":0.06,"t":0.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.19,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-embedding-97m-multilingual-r2","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-embedding-97m-multilingual-r2","u":"https://huggingface.co/ibm-granite/granite-embedding-97m-multilingual-r2"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-embedding-97m-multilingual-r2/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-embedding-97m-multilingual-r2"},{"id":"granite-embedding-311m-multilingual-r2","name":"granite-embedding-311m-multilingual-r2","hf":"ibm-granite/granite-embedding-311m-multilingual-r2","org":"ibm-granite","family":"granite","series":"granite-embedding-multilingual-r2","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-04-20","updated":"2026-05-18","gated":false,"params":{"total":0.312,"active":null,"src":"safetensors","q":null,"stTotal":0.312},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":0.62,"t":1.2},"fp8":{"w":0.33,"t":0.9},"q4":{"w":0.19,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.62,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-embedding-311m-multilingual-r2","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-embedding-311m-multilingual-r2","u":"https://huggingface.co/ibm-granite/granite-embedding-311m-multilingual-r2"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-embedding-311m-multilingual-r2/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-embedding-311m-multilingual-r2"},{"id":"granite-embedding-reranker-english-r2","name":"granite-embedding-reranker-english-r2","hf":"ibm-granite/granite-embedding-reranker-english-r2","org":"ibm-granite","family":"granite","series":"granite-embedding-reranker-english-r2","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2025-08-04","updated":"2025-11-06","gated":false,"params":{"total":0.15,"active":null,"src":"safetensors","q":null,"stTotal":0.15},"moe":false,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":0.3,"t":0.8},"fp8":{"w":0.16,"t":0.7},"q4":{"w":0.09,"t":0.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.6,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-embedding-reranker-english-r2","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-embedding-reranker-english-r2","u":"https://huggingface.co/ibm-granite/granite-embedding-reranker-english-r2"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-embedding-reranker-english-r2/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-embedding-reranker-english-r2"},{"id":"granite-embedding-small-english-r2","name":"granite-embedding-small-english-r2","hf":"ibm-granite/granite-embedding-small-english-r2","org":"ibm-granite","family":"granite","series":"granite-embedding-small-english-r2","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2025-07-17","updated":"2026-01-21","gated":false,"params":{"total":0.048,"active":null,"src":"safetensors","q":null,"stTotal":0.048},"moe":false,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":0.1,"t":0.6},"fp8":{"w":0.05,"t":0.6},"q4":{"w":0.03,"t":0.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.1,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-embedding-small-english-r2","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-embedding-small-english-r2","u":"https://huggingface.co/ibm-granite/granite-embedding-small-english-r2"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-embedding-small-english-r2/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-embedding-small-english-r2"},{"id":"granite-embedding-30m-sparse","name":"granite-embedding-30m-sparse","hf":"ibm-granite/granite-embedding-30m-sparse","org":"ibm-granite","family":"granite","series":"granite-embedding-sparse","task":"embedding","pipeline":"feature-extraction","tags":["ocr"],"released":"2025-02-17","updated":"2025-08-27","gated":false,"params":{"total":0.03,"active":null,"src":"safetensors","q":null,"stTotal":0.03},"moe":false,"ctx":514,"arch":null,"kv":null,"mem":{"bf16":{"w":0.06,"t":0.6},"fp8":{"w":0.03,"t":0.5},"q4":{"w":0.02,"t":0.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.06,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-embedding-30m-sparse","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-embedding-30m-sparse","u":"https://huggingface.co/ibm-granite/granite-embedding-30m-sparse"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-embedding-30m-sparse/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-embedding-30m-sparse"},{"id":"granite-guardian-3-0-2b","name":"granite-guardian-3.0-2b","hf":"ibm-granite/granite-guardian-3.0-2b","org":"ibm-granite","family":"granite","series":"granite-guardian-3.0","task":"guard","pipeline":"text-generation","tags":[],"released":"2024-10-15","updated":"2025-01-03","gated":false,"params":{"total":2.534,"active":null,"src":"safetensors","q":null,"stTotal":2.534},"moe":false,"ctx":8192,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67},"mem":{"bf16":{"w":5.07,"t":6.7},"fp8":{"w":2.69,"t":4.1},"q4":{"w":1.54,"t":2.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.07,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-guardian-3.0-2b","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-guardian-3.0-2b","u":"https://huggingface.co/ibm-granite/granite-guardian-3.0-2b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-guardian-3.0-2b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-guardian-3-0-2b"},{"id":"granite-guardian-3-1-2b","name":"granite-guardian-3.1-2b","hf":"ibm-granite/granite-guardian-3.1-2b","org":"ibm-granite","family":"granite","series":"granite-guardian-3.1","task":"guard","pipeline":"text-generation","tags":[],"released":"2024-12-17","updated":"2025-03-19","gated":false,"params":{"total":2.534,"active":null,"src":"safetensors","q":null,"stTotal":2.534},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":5.07,"t":6.7},"fp8":{"w":2.69,"t":4.1},"q4":{"w":1.54,"t":2.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.07,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-guardian-3.1-2b","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-guardian-3.1-2b","u":"https://huggingface.co/ibm-granite/granite-guardian-3.1-2b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-guardian-3.1-2b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-guardian-3-1-2b"},{"id":"granite-guardian-3-1-8b","name":"granite-guardian-3.1-8b","hf":"ibm-granite/granite-guardian-3.1-8b","org":"ibm-granite","family":"granite","series":"granite-guardian-3.1","task":"guard","pipeline":"text-generation","tags":[],"released":"2024-12-17","updated":"2025-09-02","gated":false,"params":{"total":8.171,"active":null,"src":"safetensors","q":null,"stTotal":8.171},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":16.34,"t":19.8},"fp8":{"w":8.68,"t":11.4},"q4":{"w":4.95,"t":7.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":16.34,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-guardian-3.1-8b","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-guardian-3.1-8b","u":"https://huggingface.co/ibm-granite/granite-guardian-3.1-8b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-guardian-3.1-8b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-guardian-3-1-8b"},{"id":"granite-guardian-3-2-5b","name":"granite-guardian-3.2-5b","hf":"ibm-granite/granite-guardian-3.2-5b","org":"ibm-granite","family":"granite","series":"granite-guardian-3.2","task":"guard","pipeline":"text-generation","tags":[],"released":"2025-01-23","updated":"2025-09-02","gated":false,"params":{"total":5.78,"active":null,"src":"safetensors","q":null,"stTotal":5.78},"moe":false,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.94,"32768":3.76,"131072":15.03},"mem":{"bf16":{"w":11.56,"t":14.2},"fp8":{"w":6.14,"t":8.2},"q4":{"w":3.5,"t":5.3}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":11.56,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-guardian-3.2-5b","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-guardian-3.2-5b","u":"https://huggingface.co/ibm-granite/granite-guardian-3.2-5b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-guardian-3.2-5b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-guardian-3-2-5b"},{"id":"granite-guardian-3-2-3b-a800m","name":"granite-guardian-3.2-3b-a800m","hf":"ibm-granite/granite-guardian-3.2-3b-a800m","org":"ibm-granite","family":"granite","series":"granite-guardian-3.2-a800m","task":"guard","pipeline":"text-generation","tags":[],"released":"2025-02-03","updated":"2025-09-02","gated":false,"params":{"total":3.299,"active":null,"src":"safetensors","q":null,"stTotal":3.299},"moe":true,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54,"32768":2.15,"131072":8.59},"mem":{"bf16":{"w":6.6,"t":8.3},"fp8":{"w":3.51,"t":4.9},"q4":{"w":2,"t":3.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.6,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-guardian-3.2-3b-a800m","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-guardian-3.2-3b-a800m","u":"https://huggingface.co/ibm-granite/granite-guardian-3.2-3b-a800m"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-guardian-3.2-3b-a800m/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-guardian-3-2-3b-a800m"},{"id":"granite-guardian-3-3-8b","name":"granite-guardian-3.3-8b","hf":"ibm-granite/granite-guardian-3.3-8b","org":"ibm-granite","family":"granite","series":"granite-guardian-3.3","task":"guard","pipeline":"text-generation","tags":[],"released":"2025-06-03","updated":"2025-09-09","gated":false,"params":{"total":8.171,"active":null,"src":"safetensors","q":null,"stTotal":8.171},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":16.34,"t":19.8},"fp8":{"w":8.68,"t":11.4},"q4":{"w":4.95,"t":7.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":16.34,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-guardian-3.3-8b","kind":"main"},{"id":"ibm-granite/granite-guardian-3.3-8b-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-guardian-3.3-8b","u":"https://huggingface.co/ibm-granite/granite-guardian-3.3-8b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-guardian-3.3-8b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-guardian-3-3-8b"},{"id":"granite-guardian-4-1-8b","name":"granite-guardian-4.1-8b","hf":"ibm-granite/granite-guardian-4.1-8b","org":"ibm-granite","family":"granite","series":"granite-guardian-4.1","task":"guard","pipeline":"text-generation","tags":[],"released":"2026-04-16","updated":"2026-08-27","gated":false,"params":{"total":8.381,"active":null,"src":"safetensors","q":null,"stTotal":8.381},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":16.76,"t":20.3},"fp8":{"w":8.9,"t":11.6},"q4":{"w":5.08,"t":7.4}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":16.76,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-guardian-4.1-8b","kind":"main"},{"id":"ibm-granite/granite-guardian-4.1-8b-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-guardian-4.1-8b","u":"https://huggingface.co/ibm-granite/granite-guardian-4.1-8b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-guardian-4.1-8b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-guardian-4-1-8b"},{"id":"granite-guardian-hap-38m","name":"granite-guardian-hap-38m","hf":"ibm-granite/granite-guardian-hap-38m","org":"ibm-granite","family":"granite","series":"granite-guardian-hap","task":"guard","pipeline":"text-classification","tags":[],"released":"2024-09-05","updated":"2024-12-19","gated":false,"params":{"total":0.038,"active":null,"src":"safetensors","q":null,"stTotal":0.038},"moe":false,"ctx":514,"arch":{"L":4,"attn":4,"slide":0,"win":null,"kvElems":1152,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.08},"mem":{"bf16":{"w":0.08,"t":0.7},"fp8":{"w":0.04,"t":0.6},"q4":{"w":0.02,"t":0.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.15,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-guardian-hap-38m","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-guardian-hap-38m","u":"https://huggingface.co/ibm-granite/granite-guardian-hap-38m"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-guardian-hap-38m/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-guardian-hap-38m"},{"id":"granite-guardian-hap-125m","name":"granite-guardian-hap-125m","hf":"ibm-granite/granite-guardian-hap-125m","org":"ibm-granite","family":"granite","series":"granite-guardian-hap","task":"guard","pipeline":"text-classification","tags":[],"released":"2024-09-05","updated":"2024-12-19","gated":false,"params":{"total":0.125,"active":null,"src":"safetensors","q":null,"stTotal":0.125},"moe":false,"ctx":514,"arch":{"L":12,"attn":12,"slide":0,"win":null,"kvElems":1536,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.3},"mem":{"bf16":{"w":0.25,"t":1.1},"fp8":{"w":0.13,"t":0.9},"q4":{"w":0.08,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.5,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-guardian-hap-125m","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-guardian-hap-125m","u":"https://huggingface.co/ibm-granite/granite-guardian-hap-125m"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-guardian-hap-125m/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-guardian-hap-125m"},{"id":"granite-speech-3-2-8b","name":"granite-speech-3.2-8b","hf":"ibm-granite/granite-speech-3.2-8b","org":"ibm-granite","family":"granite","series":"granite-speech-3.2","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-03-26","updated":"2025-04-16","gated":false,"params":{"total":8.483,"active":null,"src":"safetensors","q":null,"stTotal":8.483},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":16.97,"t":19.2},"fp8":{"w":9.01,"t":10.4},"q4":{"w":5.14,"t":6.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.04,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-speech-3.2-8b","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-speech-3.2-8b","u":"https://huggingface.co/ibm-granite/granite-speech-3.2-8b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-speech-3.2-8b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-speech-3-2-8b"},{"id":"granite-speech-3-3-2b","name":"granite-speech-3.3-2b","hf":"ibm-granite/granite-speech-3.3-2b","org":"ibm-granite","family":"granite","series":"granite-speech-3.3","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-04-28","updated":"2026-04-07","gated":false,"params":{"total":3.009,"active":null,"src":"safetensors","q":null,"stTotal":3.009},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":6.02,"t":7.1},"fp8":{"w":3.2,"t":4},"q4":{"w":1.82,"t":2.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":11.78,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-speech-3.3-2b","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-speech-3.3-2b","u":"https://huggingface.co/ibm-granite/granite-speech-3.3-2b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-speech-3.3-2b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-speech-3-3-2b"},{"id":"granite-speech-3-3-8b","name":"granite-speech-3.3-8b","hf":"ibm-granite/granite-speech-3.3-8b","org":"ibm-granite","family":"granite","series":"granite-speech-3.3","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-04-14","updated":"2026-04-02","gated":false,"params":{"total":8.649,"active":null,"src":"safetensors","q":null,"stTotal":8.649},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":17.3,"t":19.5},"fp8":{"w":9.19,"t":10.6},"q4":{"w":5.24,"t":6.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.43,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-speech-3.3-8b","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-speech-3.3-8b","u":"https://huggingface.co/ibm-granite/granite-speech-3.3-8b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-speech-3.3-8b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-speech-3-3-8b"},{"id":"granite-speech-4-1-2b","name":"granite-speech-4.1-2b","hf":"ibm-granite/granite-speech-4.1-2b","org":"ibm-granite","family":"granite","series":"granite-speech-4.1","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-04-16","updated":"2026-06-12","gated":false,"params":{"total":2.313,"active":null,"src":"safetensors","q":null,"stTotal":2.313},"moe":false,"ctx":4096,"arch":null,"kv":null,"mem":{"bf16":{"w":4.63,"t":5.6},"fp8":{"w":2.46,"t":3.2},"q4":{"w":1.4,"t":2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.83,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-speech-4.1-2b","kind":"main"},{"id":"ibm-granite/granite-speech-4.1-2b-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-speech-4.1-2b","u":"https://huggingface.co/ibm-granite/granite-speech-4.1-2b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-speech-4.1-2b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-speech-4-1-2b"},{"id":"granite-speech-4-1-2b-nar","name":"granite-speech-4.1-2b-nar","hf":"ibm-granite/granite-speech-4.1-2b-nar","org":"ibm-granite","family":"granite","series":"granite-speech-4.1-nar","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-03-10","updated":"2026-06-18","gated":false,"params":{"total":2.255,"active":null,"src":"safetensors","q":null,"stTotal":2.255},"moe":false,"ctx":4096,"arch":null,"kv":null,"mem":{"bf16":{"w":4.51,"t":5.5},"fp8":{"w":2.4,"t":3.1},"q4":{"w":1.37,"t":2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.51,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-speech-4.1-2b-nar","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-speech-4.1-2b-nar","u":"https://huggingface.co/ibm-granite/granite-speech-4.1-2b-nar"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-speech-4.1-2b-nar/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-speech-4-1-2b-nar"},{"id":"granite-speech-4-1-2b-plus","name":"granite-speech-4.1-2b-plus","hf":"ibm-granite/granite-speech-4.1-2b-plus","org":"ibm-granite","family":"granite","series":"granite-speech-4.1-plus","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-04-16","updated":"2026-10-21","gated":false,"params":{"total":2.112,"active":null,"src":"safetensors","q":null,"stTotal":2.112},"moe":false,"ctx":4096,"arch":null,"kv":null,"mem":{"bf16":{"w":4.22,"t":5.1},"fp8":{"w":2.24,"t":3},"q4":{"w":1.28,"t":1.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.22,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-speech-4.1-2b-plus","kind":"main"},{"id":"ibm-granite/granite-speech-4.1-2b-plus-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-speech-4.1-2b-plus","u":"https://huggingface.co/ibm-granite/granite-speech-4.1-2b-plus"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-speech-4.1-2b-plus/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-speech-4-1-2b-plus"},{"id":"granite-speech-5-0-2b","name":"granite-speech-5.0-2b","hf":"ibm-granite/granite-speech-5.0-2b","org":"ibm-granite","family":"granite","series":"granite-speech-5.0","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-10-07","updated":"2026-10-21","gated":false,"params":{"total":2.313,"active":null,"src":"safetensors","q":null,"stTotal":2.313},"moe":false,"ctx":16384,"arch":null,"kv":null,"mem":{"bf16":{"w":4.63,"t":5.6},"fp8":{"w":2.46,"t":3.2},"q4":{"w":1.4,"t":2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.04,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-speech-5.0-2b-GGUF","kind":"GGUF"},{"id":"ibm-granite/granite-speech-5.0-2b","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-speech-5.0-2b","u":"https://huggingface.co/ibm-granite/granite-speech-5.0-2b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-speech-5.0-2b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/granite-speech-5-0-2b/"},{"id":"granite-speech-5-0-470m-turboctc","name":"granite-speech-5.0-470m-turboctc","hf":"ibm-granite/granite-speech-5.0-470m-turboctc","org":"ibm-granite","family":"granite","series":"granite-speech-5.0-turboctc","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-08-04","updated":"2026-10-21","gated":false,"params":{"total":0.473,"active":null,"src":"safetensors","q":null,"stTotal":0.473},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.95,"t":1.5},"fp8":{"w":0.5,"t":1.1},"q4":{"w":0.29,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.95,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-speech-5.0-470m-turboctc","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-speech-5.0-470m-turboctc","u":"https://huggingface.co/ibm-granite/granite-speech-5.0-470m-turboctc"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-speech-5.0-470m-turboctc/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-speech-5-0-470m-turboctc"},{"id":"granite-speech-5-0-470m-turboctc-nc","name":"granite-speech-5.0-470m-turboctc-nc","hf":"ibm-granite/granite-speech-5.0-470m-turboctc-nc","org":"ibm-granite","family":"granite","series":"granite-speech-5.0-turboctc-nc","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-08-17","updated":"2026-10-02","gated":false,"params":{"total":0.473,"active":null,"src":"safetensors","q":null,"stTotal":0.473},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.95,"t":1.5},"fp8":{"w":0.5,"t":1.1},"q4":{"w":0.29,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.95,"native":"BF16","license":{"id":"cc-by-nc-sa-4.0","name":"CC-BY-NC-SA-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-speech-5.0-470m-turboctc-nc","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-speech-5.0-470m-turboctc-nc","u":"https://huggingface.co/ibm-granite/granite-speech-5.0-470m-turboctc-nc"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-speech-5.0-470m-turboctc-nc/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-speech-5-0-470m-turboctc-nc"},{"id":"granite-switch-4-1-8b","name":"granite-switch-4.1-8b","hf":"ibm-granite/granite-switch-4.1-8b","org":"ibm-granite","family":"granite","series":"granite-switch-4.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-10-14","updated":"2026-10-15","gated":false,"params":{"total":8.776,"active":null,"src":"safetensors","q":null,"stTotal":8.776},"moe":false,"ctx":131072,"arch":{"L":42,"attn":42,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.41,"32768":5.64,"131072":22.55},"mem":{"bf16":{"w":17.55,"t":21.2},"fp8":{"w":9.32,"t":12.2},"q4":{"w":5.32,"t":7.8}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":17.55,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-switch-4.1-8b","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-switch-4.1-8b","u":"https://huggingface.co/ibm-granite/granite-switch-4.1-8b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-switch-4.1-8b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/granite-switch-4-1-8b/"},{"id":"granite-switch-4-1-30b","name":"granite-switch-4.1-30b","hf":"ibm-granite/granite-switch-4.1-30b","org":"ibm-granite","family":"granite","series":"granite-switch-4.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-10-14","updated":"2026-10-15","gated":false,"params":{"total":29.99,"active":null,"src":"safetensors","q":null,"stTotal":29.99},"moe":false,"ctx":131072,"arch":{"L":66,"attn":66,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.21,"32768":8.86,"131072":35.43},"mem":{"bf16":{"w":59.98,"t":68.7},"fp8":{"w":31.86,"t":37.8},"q4":{"w":18.18,"t":22.7}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":59.98,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-switch-4.1-30b","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-switch-4.1-30b","u":"https://huggingface.co/ibm-granite/granite-switch-4.1-30b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-switch-4.1-30b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/granite-switch-4-1-30b/"},{"id":"granite-vision-3-2-2b","name":"granite-vision-3.2-2b","hf":"ibm-granite/granite-vision-3.2-2b","org":"ibm-granite","family":"granite","series":"granite-vision-3.2","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-02-17","updated":"2026-04-02","gated":false,"params":{"total":2.975,"active":null,"src":"safetensors","q":null,"stTotal":2.975},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":5.95,"t":7.7},"fp8":{"w":3.16,"t":4.6},"q4":{"w":1.8,"t":3.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.95,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ibm-granite/granite-vision-3.2-2b","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-vision-3.2-2b","u":"https://huggingface.co/ibm-granite/granite-vision-3.2-2b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-vision-3.2-2b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-vision-3-2-2b"},{"id":"granite-vision-3-3-2b","name":"granite-vision-3.3-2b","hf":"ibm-granite/granite-vision-3.3-2b","org":"ibm-granite","family":"granite","series":"granite-vision-3.3","task":"vlm","pipeline":"image-to-text","tags":[],"released":"2025-06-03","updated":"2026-04-02","gated":false,"params":{"total":2.975,"active":null,"src":"safetensors","q":null,"stTotal":2.975},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":5.95,"t":7.7},"fp8":{"w":3.16,"t":4.6},"q4":{"w":1.8,"t":3.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.95,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-vision-3.3-2b","kind":"main"},{"id":"ibm-granite/granite-vision-3.3-2b-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-vision-3.3-2b","u":"https://huggingface.co/ibm-granite/granite-vision-3.3-2b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-vision-3.3-2b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-vision-3-3-2b"},{"id":"granite-vision-4-1-4b","name":"granite-vision-4.1-4b","hf":"ibm-granite/granite-vision-4.1-4b","org":"ibm-granite","family":"granite","series":"granite-vision-4.1","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-04-16","updated":"2026-07-13","gated":false,"params":{"total":3.997,"active":null,"src":"safetensors","q":null,"stTotal":3.997},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":7.99,"t":10},"fp8":{"w":4.25,"t":5.8},"q4":{"w":2.42,"t":3.8}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.99,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"ibm-granite/granite-vision-4.1-4b","kind":"main"},{"id":"ibm-granite/granite-vision-4.1-4b-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · ibm-granite/granite-vision-4.1-4b","u":"https://huggingface.co/ibm-granite/granite-vision-4.1-4b"},{"t":"config.json","u":"https://huggingface.co/ibm-granite/granite-vision-4.1-4b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granite-vision-4-1-4b"},{"id":"granitelib-core-r1-0","name":"granitelib-core-r1.0","hf":"ibm-granite/granitelib-core-r1.0","org":"ibm-granite","family":"granite","series":"granitelib-core-r1.0","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-12-10","updated":"2026-10-15","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":5.82,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"ibm-granite/granitelib-core-r1.0","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granitelib-core-r1.0","u":"https://huggingface.co/ibm-granite/granitelib-core-r1.0"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granitelib-core-r1-0"},{"id":"granitelib-guardian-r1-0","name":"granitelib-guardian-r1.0","hf":"ibm-granite/granitelib-guardian-r1.0","org":"ibm-granite","family":"granite","series":"granitelib-guardian-r1.0","task":"guard","pipeline":"text-generation","tags":["reasoning"],"released":"2026-02-02","updated":"2026-10-16","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":6.22,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"ibm-granite/granitelib-guardian-r1.0","kind":"main"}],"sources":[{"t":"Hugging Face · ibm-granite/granitelib-guardian-r1.0","u":"https://huggingface.co/ibm-granite/granitelib-guardian-r1.0"}],"page":"https://aimap.page/en/models/compute/open-models/family/granite/#m-granitelib-guardian-r1-0"},{"id":"grok-2","name":"grok-2","hf":"xai-org/grok-2","org":"xai-org","family":"grok","series":"grok-2","task":"llm","pipeline":null,"tags":[],"released":"2025-08-22","updated":"2025-11-05","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":true,"ctx":131072,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59,"131072":34.36},"mem":null,"fits":null,"disk":539.03,"native":null,"license":{"id":null,"name":null,"link":"https://huggingface.co/xai-org/grok-2/blob/main/LICENSE","cls":"unknown"},"runtimes":[{"id":"sglang","via":"card"}],"variants":[{"id":"xai-org/grok-2","kind":"main"}],"sources":[{"t":"Hugging Face · xai-org/grok-2","u":"https://huggingface.co/xai-org/grok-2"},{"t":"config.json","u":"https://huggingface.co/xai-org/grok-2/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/xai-org/grok-2/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/grok/#m-grok-2"},{"id":"hy-mt1-5-1-8b","name":"HY-MT1.5-1.8B","hf":"tencent/HY-MT1.5-1.8B","org":"tencent","family":"hunyuan","series":"HY-MT1.5","task":"translate","pipeline":"translation","tags":[],"released":"2025-12-25","updated":"2026-01-01","gated":false,"params":{"total":2.039,"active":null,"src":"safetensors","q":null,"stTotal":2.039},"moe":false,"ctx":262144,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54,"32768":2.15,"131072":8.59},"mem":{"bf16":{"w":4.08,"t":5.5},"fp8":{"w":2.17,"t":3.4},"q4":{"w":1.24,"t":2.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.08,"native":"BF16","license":{"id":null,"name":null,"link":"https://huggingface.co/tencent/HY-MT1.5-1.8B/blob/main/License.txt","cls":"unknown"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"tencent/HY-MT1.5-1.8B-GGUF","kind":"GGUF"},{"id":"tencent/HY-MT1.5-1.8B","kind":"main"},{"id":"tencent/HY-MT1.5-1.8B-FP8","kind":"FP8"},{"id":"tencent/Hy-MT1.5-1.8B-1.25bit-GGUF","kind":"GGUF"},{"id":"tencent/Hy-MT1.5-1.8B-2bit-GGUF","kind":"GGUF"},{"id":"tencent/HY-MT1.5-1.8B-GPTQ-Int4","kind":"GPTQ/INT4"},{"id":"tencent/Hy-MT1.5-1.8B-2bit","kind":"main"},{"id":"tencent/Hy-MT1.5-1.8B-1.25bit","kind":"main"}],"sources":[{"t":"Hugging Face · tencent/HY-MT1.5-1.8B","u":"https://huggingface.co/tencent/HY-MT1.5-1.8B"},{"t":"config.json","u":"https://huggingface.co/tencent/HY-MT1.5-1.8B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/HY-MT1.5-1.8B/blob/main/License.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hy-mt1-5-1-8b"},{"id":"hunyuan-0-5b-instruct","name":"Hunyuan-0.5B-Instruct","hf":"tencent/Hunyuan-0.5B-Instruct","org":"tencent","family":"hunyuan","series":"Hunyuan","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-30","updated":"2025-08-06","gated":false,"params":{"total":0.539,"active":null,"src":"safetensors","q":null,"stTotal":0.539},"moe":false,"ctx":262144,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22,"131072":12.88},"mem":{"bf16":{"w":1.08,"t":2.5},"fp8":{"w":0.57,"t":1.9},"q4":{"w":0.33,"t":1.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.08,"native":"BF16","license":{"id":null,"name":null,"link":"https://huggingface.co/tencent/Hunyuan-0.5B-Instruct/blob/main/LICENSE","cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"tencent/Hunyuan-0.5B-Instruct","kind":"Instruct"},{"id":"tencent/Hunyuan-0.5B-Instruct-FP8","kind":"Instruct/FP8"},{"id":"tencent/Hunyuan-0.5B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"}],"sources":[{"t":"Hugging Face · tencent/Hunyuan-0.5B-Instruct","u":"https://huggingface.co/tencent/Hunyuan-0.5B-Instruct"},{"t":"config.json","u":"https://huggingface.co/tencent/Hunyuan-0.5B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hunyuan-0.5B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hunyuan-0-5b-instruct"},{"id":"hunyuan-1-8b-instruct","name":"Hunyuan-1.8B-Instruct","hf":"tencent/Hunyuan-1.8B-Instruct","org":"tencent","family":"hunyuan","series":"Hunyuan","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-30","updated":"2025-08-06","gated":false,"params":{"total":1.791,"active":null,"src":"safetensors","q":null,"stTotal":1.791},"moe":false,"ctx":262144,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54,"32768":2.15,"131072":8.59},"mem":{"bf16":{"w":3.58,"t":5},"fp8":{"w":1.9,"t":3.1},"q4":{"w":1.09,"t":2.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.58,"native":"BF16","license":{"id":null,"name":null,"link":"https://huggingface.co/tencent/Hunyuan-1.8B-Instruct/blob/main/LICENSE","cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"tencent/Hunyuan-1.8B-Instruct","kind":"Instruct"},{"id":"tencent/Hunyuan-1.8B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"tencent/Hunyuan-1.8B-Instruct-AWQ-Int4","kind":"Instruct/AWQ/INT4"}],"sources":[{"t":"Hugging Face · tencent/Hunyuan-1.8B-Instruct","u":"https://huggingface.co/tencent/Hunyuan-1.8B-Instruct"},{"t":"config.json","u":"https://huggingface.co/tencent/Hunyuan-1.8B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hunyuan-1.8B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hunyuan-1-8b-instruct"},{"id":"hunyuan-4b-instruct","name":"Hunyuan-4B-Instruct","hf":"tencent/Hunyuan-4B-Instruct","org":"tencent","family":"hunyuan","series":"Hunyuan","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-30","updated":"2025-10-31","gated":false,"params":{"total":4.222,"active":null,"src":"safetensors","q":null,"stTotal":4.222},"moe":false,"ctx":262144,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83,"131072":19.33},"mem":{"bf16":{"w":8.44,"t":11},"fp8":{"w":4.49,"t":6.6},"q4":{"w":2.56,"t":4.5}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.44,"native":"BF16","license":{"id":null,"name":null,"link":"https://huggingface.co/tencent/Hunyuan-4B-Instruct/blob/main/LICENSE","cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"tencent/Hunyuan-4B-Instruct","kind":"Instruct"},{"id":"tencent/Hunyuan-1.8B-Instruct-FP8","kind":"Instruct/FP8"},{"id":"tencent/Hunyuan-4B-Instruct-FP8","kind":"Instruct/FP8"},{"id":"tencent/Hunyuan-0.5B-Instruct-AWQ-Int4","kind":"Instruct/AWQ/INT4"},{"id":"tencent/Hunyuan-4B-Instruct-AWQ-Int4","kind":"Instruct/AWQ/INT4"},{"id":"tencent/Hunyuan-4B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"}],"sources":[{"t":"Hugging Face · tencent/Hunyuan-4B-Instruct","u":"https://huggingface.co/tencent/Hunyuan-4B-Instruct"},{"t":"config.json","u":"https://huggingface.co/tencent/Hunyuan-4B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hunyuan-4B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hunyuan-4b-instruct"},{"id":"hunyuan-7b-instruct","name":"Hunyuan-7B-Instruct","hf":"tencent/Hunyuan-7B-Instruct","org":"tencent","family":"hunyuan","series":"Hunyuan","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-30","updated":"2025-09-02","gated":false,"params":{"total":7.505,"active":null,"src":"safetensors","q":null,"stTotal":7.505},"moe":false,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29},"mem":{"bf16":{"w":15.01,"t":18.1},"fp8":{"w":7.97,"t":10.3},"q4":{"w":4.55,"t":6.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.01,"native":"BF16","license":{"id":null,"name":null,"link":"https://huggingface.co/tencent/Hunyuan-7B-Instruct/blob/main/LICENSE","cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"tencent/Hunyuan-7B-Instruct","kind":"Instruct"},{"id":"tencent/Hunyuan-7B-Instruct-AWQ-Int4","kind":"Instruct/AWQ/INT4"},{"id":"tencent/Hunyuan-7B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"tencent/Hunyuan-7B-Instruct-FP8","kind":"Instruct/FP8"}],"sources":[{"t":"Hugging Face · tencent/Hunyuan-7B-Instruct","u":"https://huggingface.co/tencent/Hunyuan-7B-Instruct"},{"t":"config.json","u":"https://huggingface.co/tencent/Hunyuan-7B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hunyuan-7B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hunyuan-7b-instruct"},{"id":"hunyuan-a13b-instruct","name":"Hunyuan-A13B-Instruct","hf":"tencent/Hunyuan-A13B-Instruct","org":"tencent","family":"hunyuan","series":"Hunyuan","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-25","updated":"2025-08-21","gated":false,"params":{"total":80.393,"active":13,"src":"safetensors","q":null,"stTotal":80.393},"moe":true,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29},"mem":{"bf16":{"w":160.79,"t":178.4},"fp8":{"w":85.42,"t":95.5},"q4":{"w":48.74,"t":55.2}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":160.8,"native":"BF16","license":{"id":"tencent-hunyuan-a13b","name":"tencent-hunyuan-a13b","link":"https://github.com/Tencent-Hunyuan/Hunyuan-A13B/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"tencent/Hunyuan-A13B-Instruct","kind":"Instruct"},{"id":"tencent/Hunyuan-A13B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"tencent/Hunyuan-A13B-Instruct-FP8","kind":"Instruct/FP8"},{"id":"tencent/Hunyuan-A13B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"}],"sources":[{"t":"Hugging Face · tencent/Hunyuan-A13B-Instruct","u":"https://huggingface.co/tencent/Hunyuan-A13B-Instruct"},{"t":"config.json","u":"https://huggingface.co/tencent/Hunyuan-A13B-Instruct/blob/main/config.json"},{"t":"License","u":"https://github.com/Tencent-Hunyuan/Hunyuan-A13B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hunyuan-a13b-instruct"},{"id":"hunyuan-mt-7b","name":"Hunyuan-MT-7B","hf":"tencent/Hunyuan-MT-7B","org":"tencent","family":"hunyuan","series":"Hunyuan-MT","task":"translate","pipeline":"translation","tags":[],"released":"2025-08-28","updated":"2025-12-30","gated":false,"params":{"total":8.03,"active":null,"src":"safetensors","q":null,"stTotal":8.03},"moe":false,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29},"mem":{"bf16":{"w":16.06,"t":19.2},"fp8":{"w":8.53,"t":11},"q4":{"w":4.87,"t":6.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.06,"native":"BF16","license":{"id":null,"name":null,"link":"https://huggingface.co/tencent/Hunyuan-MT-7B/blob/main/License.txt","cls":"unknown"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"tencent/Hunyuan-MT-7B","kind":"main"},{"id":"tencent/Hunyuan-MT-7B-fp8","kind":"FP8"}],"sources":[{"t":"Hugging Face · tencent/Hunyuan-MT-7B","u":"https://huggingface.co/tencent/Hunyuan-MT-7B"},{"t":"config.json","u":"https://huggingface.co/tencent/Hunyuan-MT-7B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hunyuan-MT-7B/blob/main/License.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hunyuan-mt-7b"},{"id":"hunyuan3d-part","name":"Hunyuan3D-Part","hf":"tencent/Hunyuan3D-Part","org":"tencent","family":"hunyuan","series":"Hunyuan3D-Part","task":"llm","pipeline":null,"tags":[],"released":"2025-09-23","updated":"2025-10-17","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":9.49,"native":null,"license":{"id":null,"name":null,"link":"https://huggingface.co/tencent/Hunyuan3D-Part/blob/main/LICENSE.txt","cls":"unknown"},"runtimes":[],"variants":[{"id":"tencent/Hunyuan3D-Part","kind":"main"}],"sources":[{"t":"Hugging Face · tencent/Hunyuan3D-Part","u":"https://huggingface.co/tencent/Hunyuan3D-Part"},{"t":"License","u":"https://huggingface.co/tencent/Hunyuan3D-Part/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hunyuan3d-part"},{"id":"hunyuanimage-3-0-instruct","name":"HunyuanImage-3.0-Instruct","hf":"tencent/HunyuanImage-3.0-Instruct","org":"tencent","family":"hunyuan","series":"HunyuanImage-3.0","task":"image","pipeline":"image-to-image","tags":[],"released":"2025-09-25","updated":"2026-02-03","gated":false,"params":{"total":80,"active":13,"src":"card","q":"80B total (13B active)","stTotal":83.009},"moe":true,"ctx":22800,"arch":null,"kv":null,"mem":{"bf16":{"w":160,"t":176.5},"fp8":{"w":85,"t":94},"q4":{"w":48.5,"t":53.9}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":168.54,"native":"BF16","license":{"id":"other","name":"other","link":"https://huggingface.co/tencent/HunyuanImage-3.0-Instruct/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"tencent/HunyuanImage-3.0-Instruct","kind":"Instruct"},{"id":"tencent/HunyuanImage-3.0","kind":"main"}],"sources":[{"t":"Hugging Face · tencent/HunyuanImage-3.0-Instruct","u":"https://huggingface.co/tencent/HunyuanImage-3.0-Instruct"},{"t":"config.json","u":"https://huggingface.co/tencent/HunyuanImage-3.0-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/HunyuanImage-3.0-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hunyuanimage-3-0-instruct"},{"id":"hunyuanocr","name":"HunyuanOCR","hf":"tencent/HunyuanOCR","org":"tencent","family":"hunyuan","series":"HunyuanOCR","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2025-11-18","updated":"2026-08-28","gated":false,"params":{"total":1.12,"active":null,"src":"safetensors","q":null,"stTotal":1.12},"moe":false,"ctx":131072,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22,"131072":12.88},"mem":{"bf16":{"w":2.24,"t":3.8},"fp8":{"w":1.19,"t":2.6},"q4":{"w":0.68,"t":2.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.24,"native":"BF16","license":{"id":"tencent-hunyuan-community","name":"tencent-hunyuan-community","link":"https://huggingface.co/tencent/HunyuanOCR/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"tencent/HunyuanOCR","kind":"main"}],"sources":[{"t":"Hugging Face · tencent/HunyuanOCR","u":"https://huggingface.co/tencent/HunyuanOCR"},{"t":"config.json","u":"https://huggingface.co/tencent/HunyuanOCR/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/HunyuanOCR/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hunyuanocr"},{"id":"hunyuanvideo","name":"HunyuanVideo","hf":"tencent/HunyuanVideo","org":"tencent","family":"hunyuan","series":"HunyuanVideo","task":"video","pipeline":"text-to-video","tags":[],"released":"2024-12-01","updated":"2025-03-06","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":39.81,"native":null,"license":{"id":"tencent-hunyuan-community","name":"tencent-hunyuan-community","link":"https://huggingface.co/tencent/HunyuanVideo/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"tencent/HunyuanVideo","kind":"main"}],"sources":[{"t":"Hugging Face · tencent/HunyuanVideo","u":"https://huggingface.co/tencent/HunyuanVideo"},{"t":"License","u":"https://huggingface.co/tencent/HunyuanVideo/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hunyuanvideo"},{"id":"hunyuanvideo-1-5","name":"HunyuanVideo-1.5","hf":"tencent/HunyuanVideo-1.5","org":"tencent","family":"hunyuan","series":"HunyuanVideo-1.5","task":"video","pipeline":"text-to-video","tags":[],"released":"2025-11-18","updated":"2025-12-25","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":371.76,"native":null,"license":{"id":"tencent-hunyuan-community","name":"tencent-hunyuan-community","link":"https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/master/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"tencent/HunyuanVideo-1.5","kind":"main"}],"sources":[{"t":"Hugging Face · tencent/HunyuanVideo-1.5","u":"https://huggingface.co/tencent/HunyuanVideo-1.5"},{"t":"config.json","u":"https://huggingface.co/tencent/HunyuanVideo-1.5/blob/main/config.json"},{"t":"License","u":"https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/master/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hunyuanvideo-1-5"},{"id":"hy-mt2-1-8b","name":"Hy-MT2-1.8B","hf":"tencent/Hy-MT2-1.8B","org":"tencent","family":"hunyuan","series":"Hy-MT2","task":"translate","pipeline":"translation","tags":[],"released":"2026-05-11","updated":"2026-05-26","gated":false,"params":{"total":2.039,"active":null,"src":"safetensors","q":null,"stTotal":2.039},"moe":false,"ctx":262144,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54,"32768":2.15,"131072":8.59},"mem":{"bf16":{"w":4.08,"t":5.5},"fp8":{"w":2.17,"t":3.4},"q4":{"w":1.24,"t":2.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.08,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/tencent/Hy-MT2-1.8B/blob/main/LICENSE.txt","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"tencent/Hy-MT2-1.8B-GGUF","kind":"GGUF"},{"id":"tencent/Hy-MT2-1.8B","kind":"main"},{"id":"tencent/Hy-MT2-1.8B-1.25Bit-GGUF","kind":"GGUF"},{"id":"tencent/Hy-MT2-1.8B-2Bit-GGUF","kind":"GGUF"},{"id":"tencent/Hy-MT2-1.8B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · tencent/Hy-MT2-1.8B","u":"https://huggingface.co/tencent/Hy-MT2-1.8B"},{"t":"config.json","u":"https://huggingface.co/tencent/Hy-MT2-1.8B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hy-MT2-1.8B/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hy-mt2-1-8b"},{"id":"hy-mt2-7b","name":"Hy-MT2-7B","hf":"tencent/Hy-MT2-7B","org":"tencent","family":"hunyuan","series":"Hy-MT2","task":"translate","pipeline":"translation","tags":[],"released":"2026-05-11","updated":"2026-05-26","gated":false,"params":{"total":8.03,"active":null,"src":"safetensors","q":null,"stTotal":8.03},"moe":false,"ctx":262144,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":16.06,"t":19.2},"fp8":{"w":8.53,"t":11},"q4":{"w":4.87,"t":6.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.06,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/tencent/Hy-MT2-7B/blob/main/LICENSE.txt","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"tencent/Hy-MT2-7B-GGUF","kind":"GGUF"},{"id":"tencent/Hy-MT2-7B","kind":"main"},{"id":"tencent/Hy-MT2-7B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · tencent/Hy-MT2-7B","u":"https://huggingface.co/tencent/Hy-MT2-7B"},{"t":"config.json","u":"https://huggingface.co/tencent/Hy-MT2-7B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hy-MT2-7B/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hy-mt2-7b"},{"id":"hy-mt2-30b-a3b","name":"Hy-MT2-30B-A3B","hf":"tencent/Hy-MT2-30B-A3B","org":"tencent","family":"hunyuan","series":"Hy-MT2","task":"translate","pipeline":"translation","tags":[],"released":"2026-05-11","updated":"2026-07-21","gated":false,"params":{"total":30.065,"active":3,"src":"safetensors","q":null,"stTotal":30.065},"moe":true,"ctx":262144,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22,"131072":12.88},"mem":{"bf16":{"w":60.13,"t":67.5},"fp8":{"w":31.94,"t":36.4},"q4":{"w":18.23,"t":21.4}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":60.13,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/tencent/Hy-MT2-30B-A3B/blob/main/LICENSE.txt","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"tencent/Hy-MT2-30B-A3B-GGUF","kind":"GGUF"},{"id":"tencent/Hy-MT2-30B-A3B-FP8","kind":"FP8"},{"id":"tencent/Hy-MT2-30B-A3B","kind":"main"}],"sources":[{"t":"Hugging Face · tencent/Hy-MT2-30B-A3B","u":"https://huggingface.co/tencent/Hy-MT2-30B-A3B"},{"t":"config.json","u":"https://huggingface.co/tencent/Hy-MT2-30B-A3B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hy-MT2-30B-A3B/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/hunyuan/#m-hy-mt2-30b-a3b"},{"id":"hy-memory-30b-a3b","name":"Hy-Memory-30B-A3B","hf":"tencent/Hy-Memory-30B-A3B","org":"tencent","family":"hunyuan","series":"Hy-Memory","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-10-15","updated":"2026-10-16","gated":false,"params":{"total":30.065,"active":3,"src":"safetensors","q":null,"stTotal":30.065},"moe":true,"ctx":262144,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22,"131072":12.88},"mem":{"bf16":{"w":60.13,"t":67.5},"fp8":{"w":31.94,"t":36.4},"q4":{"w":18.23,"t":21.4}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":60.13,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/tencent/Hy-Memory-30B-A3B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"tencent/Hy-Memory-30B-A3B-GGUF","kind":"GGUF"},{"id":"tencent/Hy-Memory-30B-A3B","kind":"main"},{"id":"tencent/Hy-Memory-30B-A3B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · tencent/Hy-Memory-30B-A3B","u":"https://huggingface.co/tencent/Hy-Memory-30B-A3B"},{"t":"config.json","u":"https://huggingface.co/tencent/Hy-Memory-30B-A3B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hy-Memory-30B-A3B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/hy-memory-30b-a3b/"},{"id":"hy3","name":"Hy3","hf":"tencent/Hy3","org":"tencent","family":"hunyuan","series":"Hy3","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-07-02","updated":"2026-07-20","gated":false,"params":{"total":295,"active":21,"src":"card","q":"Total Parameters 295B · Activated Parameters 21B","stTotal":298.786},"moe":true,"ctx":262144,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74,"131072":42.95},"mem":{"bf16":{"w":590,"t":652.2},"fp8":{"w":313.44,"t":348},"q4":{"w":178.84,"t":199.9}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":597.58,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/tencent/Hy3/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"tencent/Hy3","kind":"main"},{"id":"tencent/Hy3-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · tencent/Hy3","u":"https://huggingface.co/tencent/Hy3"},{"t":"config.json","u":"https://huggingface.co/tencent/Hy3/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hy3/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/hy3/"},{"id":"hy3-preview","name":"Hy3-preview","hf":"tencent/Hy3-preview","org":"tencent","family":"hunyuan","series":"Hy3-preview","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-13","updated":"2026-04-23","gated":false,"params":{"total":295,"active":21,"src":"card","q":"Total Parameters 295B · Activated Parameters 21B","stTotal":298.786},"moe":true,"ctx":262144,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74,"131072":42.95},"mem":{"bf16":{"w":590,"t":652.2},"fp8":{"w":313.44,"t":348},"q4":{"w":178.84,"t":199.9}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":597.58,"native":"BF16","license":{"id":"other","name":"other","link":"https://huggingface.co/tencent/Hy3-preview/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"tencent/Hy3-preview","kind":"main"},{"id":"tencent/Hy3-preview-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · tencent/Hy3-preview","u":"https://huggingface.co/tencent/Hy3-preview"},{"t":"config.json","u":"https://huggingface.co/tencent/Hy3-preview/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hy3-preview/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/hy3-preview/"},{"id":"hy4-preview","name":"Hy4-preview","hf":"tencent/Hy4-preview","org":"tencent","family":"hunyuan","series":"Hy4-preview","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-08-27","updated":"2026-08-28","gated":false,"params":{"total":770,"active":49,"src":"card","q":"770B total parameters, of which 49B are activated per token","stTotal":779.961},"moe":true,"ctx":1048576,"arch":{"L":78,"attn":78,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.74,"32768":2.94,"131072":11.78},"mem":{"bf16":{"w":1540,"t":1695.2},"fp8":{"w":818.12,"t":901.2},"q4":{"w":466.81,"t":514.7}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1559.98,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/tencent/Hy4-preview/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"tencent/Hy4-preview","kind":"main"},{"id":"tencent/Hy4-preview-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · tencent/Hy4-preview","u":"https://huggingface.co/tencent/Hy4-preview"},{"t":"config.json","u":"https://huggingface.co/tencent/Hy4-preview/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/tencent/Hy4-preview/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/hy4-preview/"},{"id":"inkling","name":"Inkling","hf":"thinkingmachines/Inkling","org":"thinkingmachines","family":"inkling","series":"Inkling","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-07-14","updated":"2026-07-23","gated":false,"params":{"total":975,"active":41,"src":"card","q":"975B total, 41B active","stTotal":952.378},"moe":true,"ctx":null,"arch":{"L":66,"attn":66,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":["swa_num_attention_heads"]},"kv":null,"mem":{"bf16":{"w":1950,"t":2145.5},"fp8":{"w":1035.94,"t":1140},"q4":{"w":591.09,"t":650.7}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":1904.76,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://www.apache.org/licenses/LICENSE-2.0","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"thinkingmachines/Inkling","kind":"main"},{"id":"thinkingmachines/Inkling-NVFP4","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · thinkingmachines/Inkling","u":"https://huggingface.co/thinkingmachines/Inkling"},{"t":"config.json","u":"https://huggingface.co/thinkingmachines/Inkling/blob/main/config.json"},{"t":"License","u":"https://www.apache.org/licenses/LICENSE-2.0"}],"page":"https://aimap.page/en/models/compute/open-models/inkling/"},{"id":"inkling-small","name":"Inkling-Small","hf":"thinkingmachines/Inkling-Small","org":"thinkingmachines","family":"inkling","series":"Inkling-Small","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-07-27","updated":"2026-07-31","gated":false,"params":{"total":276,"active":12,"src":"card","q":"276B total, 12B active","stTotal":265.956},"moe":true,"ctx":null,"arch":{"L":42,"attn":42,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":["swa_num_attention_heads"]},"kv":null,"mem":{"bf16":{"w":552,"t":607.7},"fp8":{"w":293.25,"t":323.1},"q4":{"w":167.32,"t":184.6}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":531.91,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://www.apache.org/licenses/LICENSE-2.0","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"thinkingmachines/Inkling-Small","kind":"main"},{"id":"thinkingmachines/Inkling-Small-NVFP4","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · thinkingmachines/Inkling-Small","u":"https://huggingface.co/thinkingmachines/Inkling-Small"},{"t":"config.json","u":"https://huggingface.co/thinkingmachines/Inkling-Small/blob/main/config.json"},{"t":"License","u":"https://www.apache.org/licenses/LICENSE-2.0"}],"page":"https://aimap.page/en/models/compute/open-models/inkling-small/"},{"id":"atria-dawn-preview","name":"Atria-Dawn-Preview","hf":"internlm/Atria-Dawn-Preview","org":"internlm","family":"internlm","series":"Atria-Dawn-Preview","task":"llm","pipeline":null,"tags":[],"released":"2026-09-11","updated":"2026-09-16","gated":false,"params":{"total":753.33,"active":null,"src":"safetensors","q":null,"stTotal":753.33},"moe":true,"ctx":1048576,"arch":{"L":78,"attn":78,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.74,"32768":2.94,"131072":11.78},"mem":{"bf16":{"w":1506.66,"t":1658.6},"fp8":{"w":800.41,"t":881.7},"q4":{"w":456.71,"t":503.6}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1506.67,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"}],"variants":[{"id":"internlm/Atria-Dawn-Preview","kind":"main"},{"id":"internlm/Atria-Dawn-Preview-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · internlm/Atria-Dawn-Preview","u":"https://huggingface.co/internlm/Atria-Dawn-Preview"},{"t":"config.json","u":"https://huggingface.co/internlm/Atria-Dawn-Preview/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/atria-dawn-preview/"},{"id":"intern-s1","name":"Intern-S1","hf":"internlm/Intern-S1","org":"internlm","family":"internlm","series":"Intern-S1","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-07-24","updated":"2026-03-29","gated":false,"params":{"total":240.71,"active":null,"src":"safetensors","q":null,"stTotal":240.71},"moe":true,"ctx":65536,"arch":{"L":94,"attn":94,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.58,"32768":6.31},"mem":{"bf16":{"w":481.42,"t":531.6},"fp8":{"w":255.75,"t":283.4},"q4":{"w":145.93,"t":162.6}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":481.42,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/internlm/Intern-S1/blob/main/LICENSE.txt","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"},{"id":"lmdeploy","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"internlm/Intern-S1","kind":"main"},{"id":"internlm/Intern-S1-FP8","kind":"FP8"},{"id":"internlm/Intern-S1-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · internlm/Intern-S1","u":"https://huggingface.co/internlm/Intern-S1"},{"t":"config.json","u":"https://huggingface.co/internlm/Intern-S1/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/internlm/Intern-S1/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/intern-s1/"},{"id":"intern-s1-pro","name":"Intern-S1-Pro","hf":"internlm/Intern-S1-Pro","org":"internlm","family":"internlm","series":"Intern-S1-Pro","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-02-02","updated":"2026-09-15","gated":false,"params":{"total":1000,"active":22,"src":"card","q":"scales to 1T total parameters … (22B activated parameters)","stTotal":917.044},"moe":true,"ctx":262144,"arch":{"L":94,"attn":94,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.58,"32768":6.31,"131072":25.23},"mem":{"bf16":{"w":2000,"t":2202.1},"fp8":{"w":1062.5,"t":1170.8},"q4":{"w":606.25,"t":669}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":919.27,"native":"F8_E4M3","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/internlm/Intern-S1-Pro/blob/main/LICENSE.txt","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"lmdeploy","via":"card"}],"variants":[{"id":"internlm/Intern-S1-Pro","kind":"main"},{"id":"internlm/Intern-S1-Pro-BF16","kind":"BF16"}],"sources":[{"t":"Hugging Face · internlm/Intern-S1-Pro","u":"https://huggingface.co/internlm/Intern-S1-Pro"},{"t":"config.json","u":"https://huggingface.co/internlm/Intern-S1-Pro/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/internlm/Intern-S1-Pro/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/intern-s1-pro/"},{"id":"intern-s1-mini","name":"Intern-S1-mini","hf":"internlm/Intern-S1-mini","org":"internlm","family":"internlm","series":"Intern-S1-mini","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-08-18","updated":"2026-03-29","gated":false,"params":{"total":8.539,"active":null,"src":"safetensors","q":null,"stTotal":8.539},"moe":false,"ctx":65536,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":17.08,"t":20.5},"fp8":{"w":9.07,"t":11.7},"q4":{"w":5.18,"t":7.4}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":17.08,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"},{"id":"lmdeploy","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"internlm/Intern-S1-mini","kind":"main"},{"id":"internlm/Intern-S1-mini-FP8","kind":"FP8"},{"id":"internlm/Intern-S1-mini-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · internlm/Intern-S1-mini","u":"https://huggingface.co/internlm/Intern-S1-mini"},{"t":"config.json","u":"https://huggingface.co/internlm/Intern-S1-mini/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/internlm/#m-intern-s1-mini"},{"id":"intern-s2-397b","name":"Intern-S2-397B","hf":"internlm/Intern-S2-397B","org":"internlm","family":"internlm","series":"Intern-S2","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-09-13","updated":"2026-09-24","gated":false,"params":{"total":403.423,"active":null,"src":"safetensors","q":null,"stTotal":403.423},"moe":true,"ctx":262144,"arch":{"L":60,"attn":15,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.25,"32768":1.01,"131072":4.03},"mem":{"bf16":{"w":806.85,"t":888.3},"fp8":{"w":428.64,"t":472.3},"q4":{"w":244.58,"t":269.8}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":806.86,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/internlm/Intern-S2/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"lmdeploy","via":"card"}],"variants":[{"id":"internlm/Intern-S2-397B","kind":"main"},{"id":"internlm/Intern-S2-397B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · internlm/Intern-S2-397B","u":"https://huggingface.co/internlm/Intern-S2-397B"},{"t":"config.json","u":"https://huggingface.co/internlm/Intern-S2-397B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/internlm/Intern-S2/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/intern-s2-397b/"},{"id":"intern-s2-mobius","name":"Intern-S2-Mobius","hf":"internlm/Intern-S2-Mobius","org":"internlm","family":"internlm","series":"Intern-S2-Mobius","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-07-29","updated":"2026-08-14","gated":false,"params":{"total":35.964,"active":null,"src":"safetensors","q":null,"stTotal":35.964},"moe":true,"ctx":262144,"arch":{"L":40,"attn":10,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.17,"32768":0.67,"131072":2.68},"mem":{"bf16":{"w":71.93,"t":79.8},"fp8":{"w":38.21,"t":42.7},"q4":{"w":21.8,"t":24.7}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":72.96,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/internlm/Intern-S2-Mobius/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"lmdeploy","via":"card"}],"variants":[{"id":"internlm/Intern-S2-Mobius","kind":"main"},{"id":"internlm/Intern-S2-Mobius-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · internlm/Intern-S2-Mobius","u":"https://huggingface.co/internlm/Intern-S2-Mobius"},{"t":"config.json","u":"https://huggingface.co/internlm/Intern-S2-Mobius/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/internlm/Intern-S2-Mobius/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/internlm/#m-intern-s2-mobius"},{"id":"intern-s2-preview","name":"Intern-S2-Preview","hf":"internlm/Intern-S2-Preview","org":"internlm","family":"internlm","series":"Intern-S2-Preview","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-05-15","updated":"2026-05-29","gated":false,"params":{"total":36.098,"active":null,"src":"safetensors","q":null,"stTotal":36.098},"moe":true,"ctx":262144,"arch":{"L":40,"attn":10,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.17,"32768":0.67,"131072":2.68},"mem":{"bf16":{"w":72.2,"t":80.1},"fp8":{"w":38.35,"t":42.9},"q4":{"w":21.88,"t":24.7}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":73.23,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/internlm/Intern-S2-Preview/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"lmdeploy","via":"card"}],"variants":[{"id":"internlm/Intern-S2-Preview","kind":"main"},{"id":"internlm/Intern-S2-Preview-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · internlm/Intern-S2-Preview","u":"https://huggingface.co/internlm/Intern-S2-Preview"},{"t":"config.json","u":"https://huggingface.co/internlm/Intern-S2-Preview/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/internlm/Intern-S2-Preview/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/internlm/#m-intern-s2-preview"},{"id":"internlm2-math-plus-7b","name":"internlm2-math-plus-7b","hf":"internlm/internlm2-math-plus-7b","org":"internlm","family":"internlm","series":"internlm2-math-plus","task":"llm","pipeline":"text-generation","tags":["math"],"released":"2024-05-24","updated":"2025-03-13","gated":false,"params":{"total":7.738,"active":null,"src":"safetensors","q":null,"stTotal":7.738},"moe":false,"ctx":8192,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07},"mem":{"bf16":{"w":15.48,"t":18.6},"fp8":{"w":8.22,"t":10.6},"q4":{"w":4.69,"t":6.7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.48,"native":"BF16","license":{"id":"other","name":"other","link":null,"cls":"custom"},"runtimes":[{"id":"transformers","via":"hf-library"}],"variants":[{"id":"internlm/internlm2-math-plus-7b","kind":"main"}],"sources":[{"t":"Hugging Face · internlm/internlm2-math-plus-7b","u":"https://huggingface.co/internlm/internlm2-math-plus-7b"},{"t":"config.json","u":"https://huggingface.co/internlm/internlm2-math-plus-7b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/internlm/#m-internlm2-math-plus-7b"},{"id":"internlm2-math-plus-mixtral8x22b","name":"internlm2-math-plus-mixtral8x22b","hf":"internlm/internlm2-math-plus-mixtral8x22b","org":"internlm","family":"internlm","series":"internlm2-math-plus-mixtral8x22b","task":"llm","pipeline":"text-generation","tags":["math"],"released":"2024-05-24","updated":"2024-05-24","gated":false,"params":{"total":140.621,"active":null,"src":"safetensors","q":null,"stTotal":140.621},"moe":true,"ctx":65536,"arch":{"L":56,"attn":56,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.88,"32768":7.52},"mem":{"bf16":{"w":281.24,"t":311.7},"fp8":{"w":149.41,"t":166.7},"q4":{"w":85.25,"t":96.2}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"h200","mac":"mac256"}},"disk":281.24,"native":"BF16","license":{"id":"other","name":"other","link":null,"cls":"custom"},"runtimes":[{"id":"transformers","via":"hf-library"}],"variants":[{"id":"internlm/internlm2-math-plus-mixtral8x22b","kind":"main"}],"sources":[{"t":"Hugging Face · internlm/internlm2-math-plus-mixtral8x22b","u":"https://huggingface.co/internlm/internlm2-math-plus-mixtral8x22b"},{"t":"config.json","u":"https://huggingface.co/internlm/internlm2-math-plus-mixtral8x22b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/internlm2-math-plus-mixtral8x22b/"},{"id":"internlm2-5-7b-chat","name":"internlm2_5-7b-chat","hf":"internlm/internlm2_5-7b-chat","org":"internlm","family":"internlm","series":"internlm2_5","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-06-27","updated":"2025-03-13","gated":false,"params":{"total":7.738,"active":null,"src":"safetensors","q":null,"stTotal":7.738},"moe":false,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29},"mem":{"bf16":{"w":15.48,"t":18.6},"fp8":{"w":8.22,"t":10.6},"q4":{"w":4.69,"t":6.7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.48,"native":"BF16","license":{"id":"other","name":"other","link":null,"cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"lmdeploy","via":"card"}],"variants":[{"id":"internlm/internlm2_5-7b-chat","kind":"Instruct"},{"id":"internlm/internlm2_5-7b","kind":"main"},{"id":"internlm/internlm2_5-7b-chat-gguf","kind":"Instruct/GGUF"},{"id":"internlm/internlm2_5-7b-chat-4bit","kind":"Instruct"}],"sources":[{"t":"Hugging Face · internlm/internlm2_5-7b-chat","u":"https://huggingface.co/internlm/internlm2_5-7b-chat"},{"t":"config.json","u":"https://huggingface.co/internlm/internlm2_5-7b-chat/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/internlm/#m-internlm2-5-7b-chat"},{"id":"internlm2-5-1-8b-chat","name":"internlm2_5-1_8b-chat","hf":"internlm/internlm2_5-1_8b-chat","org":"internlm","family":"internlm","series":"internlm2_5-1","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-07-30","updated":"2025-03-13","gated":false,"params":{"total":1.889,"active":null,"src":"safetensors","q":null,"stTotal":1.889},"moe":false,"ctx":32768,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22},"mem":{"bf16":{"w":3.78,"t":5.5},"fp8":{"w":2.01,"t":3.5},"q4":{"w":1.15,"t":2.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.78,"native":"BF16","license":{"id":"other","name":"other","link":null,"cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"lmdeploy","via":"card"}],"variants":[{"id":"internlm/internlm2_5-1_8b-chat","kind":"Instruct"},{"id":"internlm/internlm2_5-1_8b-chat-gguf","kind":"Instruct/GGUF"}],"sources":[{"t":"Hugging Face · internlm/internlm2_5-1_8b-chat","u":"https://huggingface.co/internlm/internlm2_5-1_8b-chat"},{"t":"config.json","u":"https://huggingface.co/internlm/internlm2_5-1_8b-chat/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/internlm/#m-internlm2-5-1-8b-chat"},{"id":"internlm3-8b-instruct","name":"internlm3-8b-instruct","hf":"internlm/internlm3-8b-instruct","org":"internlm","family":"internlm","series":"internlm3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-01-13","updated":"2025-02-11","gated":false,"params":{"total":8.804,"active":null,"src":"safetensors","q":null,"stTotal":8.804},"moe":false,"ctx":32768,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.4,"32768":1.61},"mem":{"bf16":{"w":17.61,"t":20.3},"fp8":{"w":9.35,"t":11.2},"q4":{"w":5.34,"t":6.8}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.61,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/internlm/internlm3-8b-instruct/blob/main/LICENSE.txt","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"},{"id":"lmdeploy","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"internlm/internlm3-8b-instruct","kind":"Instruct"},{"id":"internlm/internlm3-8b-instruct-gguf","kind":"Instruct/GGUF"},{"id":"internlm/internlm3-8b-instruct-awq","kind":"Instruct/AWQ"},{"id":"internlm/internlm3-8b-instruct-gptq-int4","kind":"Instruct/GPTQ/INT4"}],"sources":[{"t":"Hugging Face · internlm/internlm3-8b-instruct","u":"https://huggingface.co/internlm/internlm3-8b-instruct"},{"t":"config.json","u":"https://huggingface.co/internlm/internlm3-8b-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/internlm/internlm3-8b-instruct/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/internlm/#m-internlm3-8b-instruct"},{"id":"jina-code-embeddings-0-5b","name":"jina-code-embeddings-0.5b","hf":"jinaai/jina-code-embeddings-0.5b","org":"jinaai","family":"jina","series":"jina-code-embeddings","task":"embedding","pipeline":"feature-extraction","tags":["coding"],"released":"2025-08-19","updated":"2025-10-02","gated":false,"params":{"total":0.494,"active":null,"src":"safetensors","q":null,"stTotal":0.494},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":0.99,"t":1.6},"fp8":{"w":0.52,"t":1.1},"q4":{"w":0.3,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.99,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"jinaai/jina-code-embeddings-0.5b","kind":"main"},{"id":"jinaai/jina-code-embeddings-0.5b-GGUF","kind":"GGUF"},{"id":"jinaai/jina-code-embeddings-0.5b-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · jinaai/jina-code-embeddings-0.5b","u":"https://huggingface.co/jinaai/jina-code-embeddings-0.5b"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-code-embeddings-0.5b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-code-embeddings-0-5b"},{"id":"jina-code-embeddings-1-5b","name":"jina-code-embeddings-1.5b","hf":"jinaai/jina-code-embeddings-1.5b","org":"jinaai","family":"jina","series":"jina-code-embeddings","task":"embedding","pipeline":"feature-extraction","tags":["coding"],"released":"2025-08-26","updated":"2025-10-02","gated":false,"params":{"total":1.544,"active":null,"src":"safetensors","q":null,"stTotal":1.544},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":3.09,"t":3.9},"fp8":{"w":1.64,"t":2.3},"q4":{"w":0.94,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.09,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"jinaai/jina-code-embeddings-1.5b","kind":"main"},{"id":"jinaai/jina-code-embeddings-1.5b-GGUF","kind":"GGUF"},{"id":"jinaai/jina-code-embeddings-1.5b-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · jinaai/jina-code-embeddings-1.5b","u":"https://huggingface.co/jinaai/jina-code-embeddings-1.5b"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-code-embeddings-1.5b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-code-embeddings-1-5b"},{"id":"jina-colbert-v2","name":"jina-colbert-v2","hf":"jinaai/jina-colbert-v2","org":"jinaai","family":"jina","series":"jina-colbert","task":"embedding","pipeline":null,"tags":[],"released":"2024-08-16","updated":"2026-08-20","gated":false,"params":{"total":0.559,"active":null,"src":"safetensors","q":null,"stTotal":0.559},"moe":false,"ctx":8194,"arch":null,"kv":null,"mem":{"bf16":{"w":1.12,"t":1.7},"fp8":{"w":0.59,"t":1.2},"q4":{"w":0.34,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.12,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"jinaai/jina-colbert-v2","kind":"main"}],"sources":[{"t":"Hugging Face · jinaai/jina-colbert-v2","u":"https://huggingface.co/jinaai/jina-colbert-v2"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-colbert-v2/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-colbert-v2"},{"id":"jina-embeddings-v3","name":"jina-embeddings-v3","hf":"jinaai/jina-embeddings-v3","org":"jinaai","family":"jina","series":"jina-embeddings","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2024-09-05","updated":"2026-04-08","gated":false,"params":{"total":0.572,"active":null,"src":"safetensors","q":null,"stTotal":0.572},"moe":false,"ctx":8194,"arch":null,"kv":null,"mem":{"bf16":{"w":1.14,"t":1.8},"fp8":{"w":0.61,"t":1.2},"q4":{"w":0.35,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.14,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"jinaai/jina-embeddings-v3","kind":"main"},{"id":"jinaai/jina-embeddings-v3-hf","kind":"HF-transformers"}],"sources":[{"t":"Hugging Face · jinaai/jina-embeddings-v3","u":"https://huggingface.co/jinaai/jina-embeddings-v3"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-embeddings-v3/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-embeddings-v3"},{"id":"jina-embeddings-v4","name":"jina-embeddings-v4","hf":"jinaai/jina-embeddings-v4","org":"jinaai","family":"jina","series":"jina-embeddings","task":"embedding","pipeline":"visual-document-retrieval","tags":[],"released":"2025-05-07","updated":"2026-04-08","gated":false,"params":{"total":3.755,"active":null,"src":"safetensors","q":null,"stTotal":3.755},"moe":false,"ctx":128000,"arch":null,"kv":null,"mem":{"bf16":{"w":7.51,"t":8.8},"fp8":{"w":3.99,"t":4.9},"q4":{"w":2.28,"t":3}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.51,"native":"BF16","license":{"id":null,"name":null,"link":"https://huggingface.co/jinaai/jina-embeddings-v4/blob/main/LICENSE","cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"jinaai/jina-embeddings-v4","kind":"main"},{"id":"jinaai/jina-embeddings-v4-text-retrieval-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v4-text-matching-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v4-text-code-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v4-mlx-8bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · jinaai/jina-embeddings-v4","u":"https://huggingface.co/jinaai/jina-embeddings-v4"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-embeddings-v4/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/jinaai/jina-embeddings-v4/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-embeddings-v4"},{"id":"jina-embeddings-v5-omni-nano","name":"jina-embeddings-v5-omni-nano","hf":"jinaai/jina-embeddings-v5-omni-nano","org":"jinaai","family":"jina","series":"jina-embeddings-omni-nano","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-04-01","updated":"2026-10-11","gated":false,"params":{"total":0.986,"active":null,"src":"safetensors","q":null,"stTotal":0.986},"moe":false,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":1.97,"t":2.7},"fp8":{"w":1.05,"t":1.7},"q4":{"w":0.6,"t":1.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.97,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"jinaai/jina-embeddings-v5-omni-nano","kind":"main"},{"id":"jinaai/jina-embeddings-v5-omni-nano-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · jinaai/jina-embeddings-v5-omni-nano","u":"https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-embeddings-v5-omni-nano"},{"id":"jina-embeddings-v5-omni-nano-retrieval","name":"jina-embeddings-v5-omni-nano-retrieval","hf":"jinaai/jina-embeddings-v5-omni-nano-retrieval","org":"jinaai","family":"jina","series":"jina-embeddings-omni-nano-retrieval","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-03-31","updated":"2026-10-11","gated":false,"params":{"total":0.948,"active":null,"src":"safetensors","q":null,"stTotal":0.948},"moe":false,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":1.9,"t":2.6},"fp8":{"w":1.01,"t":1.6},"q4":{"w":0.57,"t":1.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.9,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"jinaai/jina-embeddings-v5-omni-nano-retrieval","kind":"main"},{"id":"jinaai/jina-embeddings-v5-omni-nano-retrieval-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v5-omni-nano-retrieval-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · jinaai/jina-embeddings-v5-omni-nano-retrieval","u":"https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano-retrieval"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano-retrieval/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-embeddings-v5-omni-nano-retrieval"},{"id":"jina-embeddings-v5-omni-small","name":"jina-embeddings-v5-omni-small","hf":"jinaai/jina-embeddings-v5-omni-small","org":"jinaai","family":"jina","series":"jina-embeddings-omni-small","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-04-01","updated":"2026-10-11","gated":false,"params":{"total":1.626,"active":null,"src":"safetensors","q":null,"stTotal":1.626},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":3.25,"t":4.1},"fp8":{"w":1.73,"t":2.4},"q4":{"w":0.99,"t":1.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.25,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"jinaai/jina-embeddings-v5-omni-small","kind":"main"},{"id":"jinaai/jina-embeddings-v5-omni-small-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · jinaai/jina-embeddings-v5-omni-small","u":"https://huggingface.co/jinaai/jina-embeddings-v5-omni-small"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-embeddings-v5-omni-small/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-embeddings-v5-omni-small"},{"id":"jina-embeddings-v5-omni-small-retrieval","name":"jina-embeddings-v5-omni-small-retrieval","hf":"jinaai/jina-embeddings-v5-omni-small-retrieval","org":"jinaai","family":"jina","series":"jina-embeddings-omni-small-retrieval","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-03-31","updated":"2026-10-11","gated":false,"params":{"total":1.559,"active":null,"src":"safetensors","q":null,"stTotal":1.559},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":3.12,"t":3.9},"fp8":{"w":1.66,"t":2.3},"q4":{"w":0.95,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.12,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"jinaai/jina-embeddings-v5-omni-small-retrieval","kind":"main"},{"id":"jinaai/jina-embeddings-v5-omni-small-retrieval-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v5-omni-small-retrieval-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · jinaai/jina-embeddings-v5-omni-small-retrieval","u":"https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-retrieval"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-retrieval/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-embeddings-v5-omni-small-retrieval"},{"id":"jina-embeddings-v5-text-nano","name":"jina-embeddings-v5-text-nano","hf":"jinaai/jina-embeddings-v5-text-nano","org":"jinaai","family":"jina","series":"jina-embeddings-text-nano","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-01-22","updated":"2026-04-15","gated":false,"params":{"total":0.212,"active":null,"src":"safetensors","q":null,"stTotal":0.212},"moe":false,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":0.42,"t":1},"fp8":{"w":0.23,"t":0.7},"q4":{"w":0.13,"t":0.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.42,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"jinaai/jina-embeddings-v5-text-nano","kind":"main"},{"id":"jinaai/jina-embeddings-v5-text-nano-retrieval","kind":"main"},{"id":"jinaai/jina-embeddings-v5-text-nano-classification","kind":"main"},{"id":"jinaai/jina-embeddings-v5-text-nano-retrieval-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v5-text-nano-text-matching","kind":"main"},{"id":"jinaai/jina-embeddings-v5-text-nano-clustering","kind":"main"},{"id":"jinaai/jina-embeddings-v5-text-nano-text-matching-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v5-text-nano-classification-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v5-text-nano-clustering-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v5-text-nano-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · jinaai/jina-embeddings-v5-text-nano","u":"https://huggingface.co/jinaai/jina-embeddings-v5-text-nano"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-embeddings-v5-text-nano/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-embeddings-v5-text-nano"},{"id":"jina-embeddings-v5-text-small","name":"jina-embeddings-v5-text-small","hf":"jinaai/jina-embeddings-v5-text-small","org":"jinaai","family":"jina","series":"jina-embeddings-text-small","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-01-22","updated":"2026-04-15","gated":false,"params":{"total":0.596,"active":null,"src":"safetensors","q":null,"stTotal":0.596},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":1.19,"t":1.8},"fp8":{"w":0.63,"t":1.2},"q4":{"w":0.36,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.19,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"jinaai/jina-embeddings-v5-text-small","kind":"main"},{"id":"jinaai/jina-embeddings-v5-text-small-retrieval","kind":"main"},{"id":"jinaai/jina-embeddings-v5-text-small-text-matching","kind":"main"},{"id":"jinaai/jina-embeddings-v5-text-small-classification","kind":"main"},{"id":"jinaai/jina-embeddings-v5-text-small-clustering","kind":"main"},{"id":"jinaai/jina-embeddings-v5-text-small-retrieval-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v5-text-small-clustering-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v5-text-small-classification-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v5-text-small-text-matching-GGUF","kind":"GGUF"},{"id":"jinaai/jina-embeddings-v5-text-small-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · jinaai/jina-embeddings-v5-text-small","u":"https://huggingface.co/jinaai/jina-embeddings-v5-text-small"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-embeddings-v5-text-small/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-embeddings-v5-text-small"},{"id":"jina-embeddings-v4-vllm-retrieval","name":"jina-embeddings-v4-vllm-retrieval","hf":"jinaai/jina-embeddings-v4-vllm-retrieval","org":"jinaai","family":"jina","series":"jina-embeddings-vllm-retrieval","task":"embedding","pipeline":"visual-document-retrieval","tags":[],"released":"2025-07-01","updated":"2025-09-17","gated":false,"params":{"total":3.755,"active":null,"src":"safetensors","q":null,"stTotal":3.755},"moe":false,"ctx":128000,"arch":null,"kv":null,"mem":{"bf16":{"w":7.51,"t":8.8},"fp8":{"w":3.99,"t":4.9},"q4":{"w":2.28,"t":3}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.51,"native":"BF16","license":{"id":null,"name":null,"link":null,"cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"jinaai/jina-embeddings-v4-vllm-retrieval","kind":"main"}],"sources":[{"t":"Hugging Face · jinaai/jina-embeddings-v4-vllm-retrieval","u":"https://huggingface.co/jinaai/jina-embeddings-v4-vllm-retrieval"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-embeddings-v4-vllm-retrieval/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-embeddings-v4-vllm-retrieval"},{"id":"jina-reranker-v3-5","name":"jina-reranker-v3.5","hf":"jinaai/jina-reranker-v3.5","org":"jinaai","family":"jina","series":"jina-reranker","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2026-07-14","updated":"2026-07-30","gated":false,"params":{"total":0.597,"active":null,"src":"safetensors","q":null,"stTotal":0.597},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":1.19,"t":1.8},"fp8":{"w":0.63,"t":1.2},"q4":{"w":0.36,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.19,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"jinaai/jina-reranker-v3.5","kind":"main"},{"id":"jinaai/jina-reranker-v3.5-GGUF","kind":"GGUF"},{"id":"jinaai/jina-reranker-v3.5-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · jinaai/jina-reranker-v3.5","u":"https://huggingface.co/jinaai/jina-reranker-v3.5"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-reranker-v3.5/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-reranker-v3-5"},{"id":"jina-reranker-v3","name":"jina-reranker-v3","hf":"jinaai/jina-reranker-v3","org":"jinaai","family":"jina","series":"jina-reranker","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2025-09-18","updated":"2026-08-10","gated":false,"params":{"total":0.597,"active":null,"src":"safetensors","q":null,"stTotal":0.597},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":1.19,"t":1.8},"fp8":{"w":0.63,"t":1.2},"q4":{"w":0.36,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.19,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"jinaai/jina-reranker-v3","kind":"main"},{"id":"jinaai/jina-reranker-v3-GGUF","kind":"GGUF"},{"id":"jinaai/jina-reranker-v3-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · jinaai/jina-reranker-v3","u":"https://huggingface.co/jinaai/jina-reranker-v3"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-reranker-v3/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-reranker-v3"},{"id":"jina-reranker-m0","name":"jina-reranker-m0","hf":"jinaai/jina-reranker-m0","org":"jinaai","family":"jina","series":"jina-reranker-m0","task":"rerank","pipeline":"text-classification","tags":[],"released":"2025-03-27","updated":"2026-04-09","gated":false,"params":{"total":2.445,"active":null,"src":"safetensors","q":null,"stTotal":2.445},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":4.89,"t":5.9},"fp8":{"w":2.6,"t":3.4},"q4":{"w":1.48,"t":2.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.89,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"jinaai/jina-reranker-m0","kind":"main"},{"id":"jinaai/jina-reranker-m0-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · jinaai/jina-reranker-m0","u":"https://huggingface.co/jinaai/jina-reranker-m0"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-reranker-m0/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-reranker-m0"},{"id":"jina-reranker-v2-base-multilingual","name":"jina-reranker-v2-base-multilingual","hf":"jinaai/jina-reranker-v2-base-multilingual","org":"jinaai","family":"jina","series":"jina-reranker-multilingual","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2024-06-19","updated":"2025-10-21","gated":false,"params":{"total":0.278,"active":null,"src":"safetensors","q":null,"stTotal":0.278},"moe":false,"ctx":1026,"arch":null,"kv":null,"mem":{"bf16":{"w":0.56,"t":1.1},"fp8":{"w":0.3,"t":0.8},"q4":{"w":0.17,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.56,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"jinaai/jina-reranker-v2-base-multilingual","kind":"Base"}],"sources":[{"t":"Hugging Face · jinaai/jina-reranker-v2-base-multilingual","u":"https://huggingface.co/jinaai/jina-reranker-v2-base-multilingual"},{"t":"config.json","u":"https://huggingface.co/jinaai/jina-reranker-v2-base-multilingual/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/jina/#m-jina-reranker-v2-base-multilingual"},{"id":"kimi-audio-7b-instruct","name":"Kimi-Audio-7B-Instruct","hf":"moonshotai/Kimi-Audio-7B-Instruct","org":"moonshotai","family":"kimi","series":"Kimi-Audio","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2025-04-25","updated":"2025-05-29","gated":false,"params":{"total":9.766,"active":null,"src":"safetensors","q":null,"stTotal":9.766},"moe":false,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":19.53,"t":22},"fp8":{"w":10.38,"t":11.9},"q4":{"w":5.92,"t":7}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":19.53,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"moonshotai/Kimi-Audio-7B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-Audio-7B-Instruct","u":"https://huggingface.co/moonshotai/Kimi-Audio-7B-Instruct"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-Audio-7B-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/kimi/#m-kimi-audio-7b-instruct"},{"id":"kimi-dev-72b","name":"Kimi-Dev-72B","hf":"moonshotai/Kimi-Dev-72B","org":"moonshotai","family":"kimi","series":"Kimi-Dev","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-16","updated":"2025-06-17","gated":false,"params":{"total":72.706,"active":null,"src":"safetensors","q":null,"stTotal":72.706},"moe":false,"ctx":131072,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74,"131072":42.95},"mem":{"bf16":{"w":145.41,"t":163.1},"fp8":{"w":77.25,"t":88.2},"q4":{"w":44.08,"t":51.7}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":145.41,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/moonshotai/Kimi-Dev-72B/blob/main/LICENSE.md","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-Dev-72B","kind":"main"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-Dev-72B","u":"https://huggingface.co/moonshotai/Kimi-Dev-72B"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-Dev-72B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/moonshotai/Kimi-Dev-72B/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/kimi/#m-kimi-dev-72b"},{"id":"kimi-k2-instruct","name":"Kimi-K2-Instruct","hf":"moonshotai/Kimi-K2-Instruct","org":"moonshotai","family":"kimi","series":"Kimi-K2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-11","updated":"2026-04-23","gated":false,"params":{"total":1000,"active":32,"src":"card","q":"32 billion activated parameters and 1 trillion total parameters","stTotal":1026.408},"moe":true,"ctx":131072,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":2000,"t":2201.1},"fp8":{"w":1062.5,"t":1169.8},"q4":{"w":606.25,"t":668}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":1029.19,"native":"F8_E4M3","license":{"id":"modified-mit","name":"modified-mit","link":"https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-K2-Instruct","kind":"Instruct"},{"id":"moonshotai/Kimi-K2-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-K2-Instruct","u":"https://huggingface.co/moonshotai/Kimi-K2-Instruct"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/kimi-k2-instruct/"},{"id":"kimi-k2-instruct-0905","name":"Kimi-K2-Instruct-0905","hf":"moonshotai/Kimi-K2-Instruct-0905","org":"moonshotai","family":"kimi","series":"Kimi-K2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-03","updated":"2026-01-30","gated":false,"params":{"total":1000,"active":32,"src":"card","q":"32 billion activated parameters and a total of 1 trillion parameters","stTotal":1026.408},"moe":true,"ctx":262144,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":2000,"t":2201.1},"fp8":{"w":1062.5,"t":1169.8},"q4":{"w":606.25,"t":668}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":1029.19,"native":"F8_E4M3","license":{"id":"modified-mit","name":"modified-mit","link":"https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-K2-Instruct-0905","kind":"Instruct"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-K2-Instruct-0905","u":"https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/kimi-k2-instruct-0905/"},{"id":"kimi-k2-thinking","name":"Kimi-K2-Thinking","hf":"moonshotai/Kimi-K2-Thinking","org":"moonshotai","family":"kimi","series":"Kimi-K2-Thinking","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-11-04","updated":"2026-01-30","gated":false,"params":{"total":1000,"active":32,"src":"card","q":"Total Parameters 1T · Activated Parameters 32B","stTotal":1026.408},"moe":true,"ctx":262144,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":2000,"t":2201.1},"fp8":{"w":1062.5,"t":1169.8},"q4":{"w":606.25,"t":668}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":594.23,"native":"I32","license":{"id":"modified-mit","name":"modified-mit","link":"https://huggingface.co/moonshotai/Kimi-K2-Thinking/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-K2-Thinking","kind":"main"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-K2-Thinking","u":"https://huggingface.co/moonshotai/Kimi-K2-Thinking"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-K2-Thinking/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/moonshotai/Kimi-K2-Thinking/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/kimi-k2-thinking/"},{"id":"kimi-k2-5","name":"Kimi-K2.5","hf":"moonshotai/Kimi-K2.5","org":"moonshotai","family":"kimi","series":"Kimi-K2.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-01-01","updated":"2026-04-30","gated":false,"params":{"total":1000,"active":32,"src":"card","q":"Total Parameters 1T · Activated Parameters 32B","stTotal":1026.879},"moe":true,"ctx":262144,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":2000,"t":2201.1},"fp8":{"w":1062.5,"t":1169.8},"q4":{"w":606.25,"t":668}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":595.18,"native":"I32","license":{"id":"modified-mit","name":"modified-mit","link":"https://huggingface.co/moonshotai/Kimi-K2.5/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-K2.5","kind":"main"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-K2.5","u":"https://huggingface.co/moonshotai/Kimi-K2.5"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-K2.5/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/moonshotai/Kimi-K2.5/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/kimi-k2-5/"},{"id":"kimi-k2-6","name":"Kimi-K2.6","hf":"moonshotai/Kimi-K2.6","org":"moonshotai","family":"kimi","series":"Kimi-K2.6","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-04-14","updated":"2026-05-19","gated":false,"params":{"total":1000,"active":32,"src":"card","q":"Total Parameters 1T · Activated Parameters 32B","stTotal":1026.879},"moe":true,"ctx":262144,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":2000,"t":2201.1},"fp8":{"w":1062.5,"t":1169.8},"q4":{"w":606.25,"t":668}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":595.18,"native":"I32","license":{"id":"modified-mit","name":"modified-mit","link":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-K2.6","kind":"main"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-K2.6","u":"https://huggingface.co/moonshotai/Kimi-K2.6"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/kimi-k2-6/"},{"id":"kimi-k2-7-code","name":"Kimi-K2.7-Code","hf":"moonshotai/Kimi-K2.7-Code","org":"moonshotai","family":"kimi","series":"Kimi-K2.7-Code","task":"vlm","pipeline":"image-text-to-text","tags":["coding"],"released":"2026-06-11","updated":"2026-06-15","gated":false,"params":{"total":1000,"active":32,"src":"card","q":"Total Parameters 1T · Activated Parameters 32B","stTotal":1026.879},"moe":true,"ctx":262144,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":2000,"t":2201.1},"fp8":{"w":1062.5,"t":1169.8},"q4":{"w":606.25,"t":668}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":595.18,"native":"I32","license":{"id":"modified-mit","name":"modified-mit","link":"https://huggingface.co/moonshotai/Kimi-K2.7-Code/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-K2.7-Code","kind":"main"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-K2.7-Code","u":"https://huggingface.co/moonshotai/Kimi-K2.7-Code"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-K2.7-Code/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/moonshotai/Kimi-K2.7-Code/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/kimi-k2-7-code/"},{"id":"kimi-k3","name":"Kimi-K3","hf":"moonshotai/Kimi-K3","org":"moonshotai","family":"kimi","series":"Kimi-K3","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-06-13","updated":"2026-09-02","gated":false,"params":{"total":2800,"active":104,"src":"card","q":"Total Parameters 2.8T · Activated Parameters 104B","stTotal":2779.932},"moe":true,"ctx":1048576,"arch":{"L":93,"attn":24,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla+hybrid","exotic":[]},"kv":{"8192":0.23,"32768":0.91,"131072":3.62},"mem":{"bf16":{"w":5600,"t":6160.7},"fp8":{"w":2975,"t":3273.2},"q4":{"w":1697.5,"t":1868}},"fits":{"bf16":{"gpu":null,"mac":null},"fp8":{"gpu":"2x8xb300","mac":null},"q4":{"gpu":"8xb300","mac":null}},"disk":1560.94,"native":"U8","license":{"id":"kimi-k3","name":"kimi-k3","link":"https://huggingface.co/moonshotai/Kimi-K3/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-K3","kind":"main"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-K3","u":"https://huggingface.co/moonshotai/Kimi-K3"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-K3/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/moonshotai/Kimi-K3/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/kimi-k3/"},{"id":"kimi-linear-48b-a3b-instruct","name":"Kimi-Linear-48B-A3B-Instruct","hf":"moonshotai/Kimi-Linear-48B-A3B-Instruct","org":"moonshotai","family":"kimi","series":"Kimi-Linear","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-10-30","updated":"2025-12-16","gated":false,"params":{"total":49.123,"active":3,"src":"safetensors","q":null,"stTotal":49.123},"moe":true,"ctx":null,"arch":{"L":27,"attn":7,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla+hybrid","exotic":[]},"kv":{"8192":0.07,"32768":0.26,"131072":1.06},"mem":{"bf16":{"w":98.25,"t":108.6},"fp8":{"w":52.19,"t":58},"q4":{"w":29.78,"t":33.3}},"fits":{"bf16":{"gpu":"h200","mac":"mac256"},"fp8":{"gpu":"h100","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac64"}},"disk":98.25,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-Linear-48B-A3B-Instruct","kind":"Instruct"},{"id":"moonshotai/Kimi-Linear-48B-A3B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-Linear-48B-A3B-Instruct","u":"https://huggingface.co/moonshotai/Kimi-Linear-48B-A3B-Instruct"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-Linear-48B-A3B-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/kimi/#m-kimi-linear-48b-a3b-instruct"},{"id":"kimi-vl-a3b-instruct","name":"Kimi-VL-A3B-Instruct","hf":"moonshotai/Kimi-VL-A3B-Instruct","org":"moonshotai","family":"kimi","series":"Kimi-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-04-09","updated":"2026-01-30","gated":false,"params":{"total":16.408,"active":3,"src":"safetensors","q":null,"stTotal":16.408},"moe":true,"ctx":131072,"arch":{"L":27,"attn":27,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.25,"32768":1.02,"131072":4.08},"mem":{"bf16":{"w":32.82,"t":36.8},"fp8":{"w":17.43,"t":19.9},"q4":{"w":9.95,"t":11.7}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":32.82,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-VL-A3B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-VL-A3B-Instruct","u":"https://huggingface.co/moonshotai/Kimi-VL-A3B-Instruct"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-VL-A3B-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/kimi/#m-kimi-vl-a3b-instruct"},{"id":"kimi-vl-a3b-thinking","name":"Kimi-VL-A3B-Thinking","hf":"moonshotai/Kimi-VL-A3B-Thinking","org":"moonshotai","family":"kimi","series":"Kimi-VL-Thinking","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-04-09","updated":"2026-01-30","gated":false,"params":{"total":16.408,"active":3,"src":"safetensors","q":null,"stTotal":16.408},"moe":true,"ctx":131072,"arch":{"L":27,"attn":27,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.25,"32768":1.02,"131072":4.08},"mem":{"bf16":{"w":32.82,"t":36.8},"fp8":{"w":17.43,"t":19.9},"q4":{"w":9.95,"t":11.7}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":32.82,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-VL-A3B-Thinking","kind":"main"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-VL-A3B-Thinking","u":"https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/kimi/#m-kimi-vl-a3b-thinking"},{"id":"kimi-vl-a3b-thinking-2506","name":"Kimi-VL-A3B-Thinking-2506","hf":"moonshotai/Kimi-VL-A3B-Thinking-2506","org":"moonshotai","family":"kimi","series":"Kimi-VL-Thinking","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-06-21","updated":"2026-01-30","gated":false,"params":{"total":16.408,"active":3,"src":"safetensors","q":null,"stTotal":16.408},"moe":true,"ctx":131072,"arch":{"L":27,"attn":27,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.25,"32768":1.02,"131072":4.08},"mem":{"bf16":{"w":32.82,"t":36.8},"fp8":{"w":17.43,"t":19.9},"q4":{"w":9.95,"t":11.7}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":32.82,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"moonshotai/Kimi-VL-A3B-Thinking-2506","kind":"main"}],"sources":[{"t":"Hugging Face · moonshotai/Kimi-VL-A3B-Thinking-2506","u":"https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking-2506"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking-2506/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/kimi/#m-kimi-vl-a3b-thinking-2506"},{"id":"moonlight-16b-a3b-instruct","name":"Moonlight-16B-A3B-Instruct","hf":"moonshotai/Moonlight-16B-A3B-Instruct","org":"moonshotai","family":"kimi","series":"Moonlight","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-02-22","updated":"2026-01-30","gated":false,"params":{"total":15.96,"active":3,"src":"safetensors","q":null,"stTotal":15.96},"moe":true,"ctx":8192,"arch":{"L":27,"attn":27,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.25},"mem":{"bf16":{"w":31.92,"t":35.9},"fp8":{"w":16.96,"t":19.4},"q4":{"w":9.68,"t":11.4}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":31.92,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"moonshotai/Moonlight-16B-A3B-Instruct","kind":"Instruct"},{"id":"moonshotai/Moonlight-16B-A3B","kind":"main"}],"sources":[{"t":"Hugging Face · moonshotai/Moonlight-16B-A3B-Instruct","u":"https://huggingface.co/moonshotai/Moonlight-16B-A3B-Instruct"},{"t":"config.json","u":"https://huggingface.co/moonshotai/Moonlight-16B-A3B-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/kimi/#m-moonlight-16b-a3b-instruct"},{"id":"laguna-m-1","name":"Laguna-M.1","hf":"poolside/Laguna-M.1","org":"poolside","family":"laguna","series":"Laguna-M.1","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2026-06-15","updated":"2026-07-14","gated":false,"params":{"total":225,"active":23,"src":"card","q":"225B total parameters and 23B activated parameters per token","stTotal":225.796},"moe":true,"ctx":262144,"arch":{"L":70,"attn":70,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.35,"32768":9.4,"131072":37.58},"mem":{"bf16":{"w":450,"t":497.9},"fp8":{"w":239.06,"t":265.8},"q4":{"w":136.41,"t":152.9}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":451.6,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/poolside/Laguna-M.1/blob/main/LICENSE.md","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"poolside/Laguna-M.1","kind":"main"},{"id":"poolside/Laguna-M.1-NVFP4","kind":"NVFP4"},{"id":"poolside/Laguna-M.1-FP8","kind":"FP8"},{"id":"poolside/Laguna-M.1-base","kind":"Base"}],"sources":[{"t":"Hugging Face · poolside/Laguna-M.1","u":"https://huggingface.co/poolside/Laguna-M.1"},{"t":"config.json","u":"https://huggingface.co/poolside/Laguna-M.1/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/poolside/Laguna-M.1/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/laguna-m-1/"},{"id":"laguna-s-2-1","name":"Laguna-S-2.1","hf":"poolside/Laguna-S-2.1","org":"poolside","family":"laguna","series":"Laguna-S-2.1","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2026-07-13","updated":"2026-08-19","gated":false,"params":{"total":118,"active":8,"src":"card","q":"118B total, ~8B activated per token","stTotal":117.562},"moe":true,"ctx":1048576,"arch":{"L":48,"attn":12,"slide":36,"win":512,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.48,"32768":1.69,"131072":6.52},"mem":{"bf16":{"w":236,"t":260.6},"fp8":{"w":125.38,"t":138.9},"q4":{"w":71.54,"t":79.7}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":235.13,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://huggingface.co/poolside/Laguna-S-2.1/blob/main/LICENSE.md","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"},{"id":"ollama","via":"ollama-library","tag":"laguna-s-2.1","url":"https://ollama.com/library/laguna-s-2.1"}],"variants":[{"id":"poolside/Laguna-S-2.1-GGUF","kind":"GGUF"},{"id":"poolside/Laguna-S-2.1","kind":"main"},{"id":"poolside/Laguna-S-2.1-NVFP4","kind":"NVFP4"},{"id":"poolside/Laguna-S-2.1-DFlash-NVFP4","kind":"NVFP4"},{"id":"poolside/Laguna-S-2.1-FP8","kind":"FP8"},{"id":"poolside/Laguna-S-2.1-INT4","kind":"INT4"},{"id":"poolside/Laguna-S-2.1-NVFP4-mlx","kind":"NVFP4/MLX"},{"id":"poolside/Laguna-S-2.1-DFlash-FP8","kind":"FP8"},{"id":"poolside/Laguna-S-2.1-DFlash-INT4","kind":"INT4"}],"sources":[{"t":"Hugging Face · poolside/Laguna-S-2.1","u":"https://huggingface.co/poolside/Laguna-S-2.1"},{"t":"config.json","u":"https://huggingface.co/poolside/Laguna-S-2.1/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/poolside/Laguna-S-2.1/blob/main/LICENSE.md"},{"t":"Ollama library · laguna-s-2.1","u":"https://ollama.com/library/laguna-s-2.1"}],"page":"https://aimap.page/en/models/compute/open-models/laguna-s-2-1/"},{"id":"laguna-xs-2-1","name":"Laguna-XS-2.1","hf":"poolside/Laguna-XS-2.1","org":"poolside","family":"laguna","series":"Laguna-XS-2.1","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2026-06-20","updated":"2026-08-19","gated":false,"params":{"total":33,"active":3,"src":"card","q":"33B total with 3B activated per token","stTotal":33.443},"moe":true,"ctx":262144,"arch":{"L":40,"attn":10,"slide":30,"win":512,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.4,"32768":1.41,"131072":5.43},"mem":{"bf16":{"w":66,"t":73.5},"fp8":{"w":35.06,"t":39.5},"q4":{"w":20.01,"t":22.9}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":66.89,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://huggingface.co/poolside/Laguna-XS-2.1/blob/main/LICENSE.md","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"},{"id":"ollama","via":"ollama-library","tag":"laguna-xs-2.1","url":"https://ollama.com/library/laguna-xs-2.1"}],"variants":[{"id":"poolside/Laguna-XS-2.1","kind":"main"},{"id":"poolside/Laguna-XS-2.1-GGUF","kind":"GGUF"},{"id":"poolside/Laguna-XS-2.1-NVFP4","kind":"NVFP4"},{"id":"poolside/Laguna-XS-2.1-FP8","kind":"FP8"},{"id":"poolside/Laguna-XS-2.1-INT4","kind":"INT4"},{"id":"poolside/Laguna-XS-2.1-NVFP4-mlx","kind":"NVFP4/MLX"},{"id":"poolside/Laguna-XS-2.1-DFlash-NVFP4","kind":"NVFP4"},{"id":"poolside/Laguna-XS-2.1-DFlash-FP8","kind":"FP8"},{"id":"poolside/Laguna-XS-2.1-DFlash-INT4","kind":"INT4"}],"sources":[{"t":"Hugging Face · poolside/Laguna-XS-2.1","u":"https://huggingface.co/poolside/Laguna-XS-2.1"},{"t":"config.json","u":"https://huggingface.co/poolside/Laguna-XS-2.1/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/poolside/Laguna-XS-2.1/blob/main/LICENSE.md"},{"t":"Ollama library · laguna-xs-2.1","u":"https://ollama.com/library/laguna-xs-2.1"}],"page":"https://aimap.page/en/models/compute/open-models/family/laguna/#m-laguna-xs-2-1"},{"id":"laguna-xs-2","name":"Laguna-XS.2","hf":"poolside/Laguna-XS.2","org":"poolside","family":"laguna","series":"Laguna-XS.2","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2026-04-23","updated":"2026-09-22","gated":false,"params":{"total":33,"active":3,"src":"card","q":"33B total with 3B activated per token","stTotal":33.443},"moe":true,"ctx":262144,"arch":{"L":40,"attn":10,"slide":30,"win":512,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.4,"32768":1.41,"131072":5.43},"mem":{"bf16":{"w":66,"t":73.5},"fp8":{"w":35.06,"t":39.5},"q4":{"w":20.01,"t":22.9}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":66.89,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/poolside/Laguna-XS.2/blob/main/LICENSE.md","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"},{"id":"ollama","via":"ollama-library","tag":"laguna-xs.2","url":"https://ollama.com/library/laguna-xs.2"}],"variants":[{"id":"poolside/Laguna-XS.2","kind":"main"},{"id":"poolside/Laguna-XS.2-NVFP4","kind":"NVFP4"},{"id":"poolside/Laguna-XS.2-FP8","kind":"FP8"},{"id":"poolside/Laguna-XS.2-INT4","kind":"INT4"}],"sources":[{"t":"Hugging Face · poolside/Laguna-XS.2","u":"https://huggingface.co/poolside/Laguna-XS.2"},{"t":"config.json","u":"https://huggingface.co/poolside/Laguna-XS.2/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/poolside/Laguna-XS.2/blob/main/LICENSE.md"},{"t":"Ollama library · laguna-xs.2","u":"https://ollama.com/library/laguna-xs.2"}],"page":"https://aimap.page/en/models/compute/open-models/family/laguna/#m-laguna-xs-2"},{"id":"lfm2-350m","name":"LFM2-350M","hf":"LiquidAI/LFM2-350M","org":"LiquidAI","family":"lfm","series":"LFM2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-10","updated":"2026-08-05","gated":false,"params":{"total":0.354,"active":null,"src":"safetensors","q":null,"stTotal":0.354},"moe":false,"ctx":128000,"arch":{"L":16,"attn":16,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.27,"32768":1.07},"mem":{"bf16":{"w":0.71,"t":1.5},"fp8":{"w":0.38,"t":1.2},"q4":{"w":0.21,"t":1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.71,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2-350M/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2-350M","kind":"main"},{"id":"LiquidAI/LFM2-350M-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2-350M","u":"https://huggingface.co/LiquidAI/LFM2-350M"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2-350M/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2-350M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-350m"},{"id":"lfm2-700m","name":"LFM2-700M","hf":"LiquidAI/LFM2-700M","org":"LiquidAI","family":"lfm","series":"LFM2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-10","updated":"2026-08-05","gated":false,"params":{"total":0.742,"active":null,"src":"safetensors","q":null,"stTotal":0.742},"moe":false,"ctx":128000,"arch":{"L":16,"attn":16,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.27,"32768":1.07},"mem":{"bf16":{"w":1.48,"t":2.4},"fp8":{"w":0.79,"t":1.6},"q4":{"w":0.45,"t":1.3}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.48,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2-700M/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2-700M-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2-700M","kind":"main"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2-700M","u":"https://huggingface.co/LiquidAI/LFM2-700M"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2-700M/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2-700M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-700m"},{"id":"lfm2-1-2b","name":"LFM2-1.2B","hf":"LiquidAI/LFM2-1.2B","org":"LiquidAI","family":"lfm","series":"LFM2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-10","updated":"2026-08-05","gated":false,"params":{"total":1.17,"active":null,"src":"safetensors","q":null,"stTotal":1.17},"moe":false,"ctx":128000,"arch":{"L":16,"attn":16,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.27,"32768":1.07},"mem":{"bf16":{"w":2.34,"t":3.3},"fp8":{"w":1.24,"t":2.1},"q4":{"w":0.71,"t":1.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.34,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2-1.2B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2-1.2B","kind":"main"},{"id":"LiquidAI/LFM2-1.2B-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2-1.2B","u":"https://huggingface.co/LiquidAI/LFM2-1.2B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2-1.2B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2-1.2B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-1-2b"},{"id":"lfm2-2-6b","name":"LFM2-2.6B","hf":"LiquidAI/LFM2-2.6B","org":"LiquidAI","family":"lfm","series":"LFM2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-22","updated":"2026-08-05","gated":false,"params":{"total":2.569,"active":null,"src":"safetensors","q":null,"stTotal":2.569},"moe":false,"ctx":128000,"arch":{"L":30,"attn":8,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.13,"32768":0.54},"mem":{"bf16":{"w":5.14,"t":6.3},"fp8":{"w":2.73,"t":3.6},"q4":{"w":1.56,"t":2.3}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.14,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2-2.6B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2-2.6B-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2-2.6B","kind":"main"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2-2.6B","u":"https://huggingface.co/LiquidAI/LFM2-2.6B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2-2.6B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2-2.6B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-2-6b"},{"id":"lfm2-8b-a1b","name":"LFM2-8B-A1B","hf":"LiquidAI/LFM2-8B-A1B","org":"LiquidAI","family":"lfm","series":"LFM2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-10-07","updated":"2026-08-05","gated":false,"params":{"total":8.34,"active":1,"src":"safetensors","q":null,"stTotal":8.34},"moe":true,"ctx":128000,"arch":{"L":24,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":16.68,"t":18.9},"fp8":{"w":8.86,"t":10.3},"q4":{"w":5.06,"t":6.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.68,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2-8B-A1B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2-8B-A1B","kind":"main"},{"id":"LiquidAI/LFM2-8B-A1B-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2-8B-A1B-ONNX","kind":"ONNX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2-8B-A1B","u":"https://huggingface.co/LiquidAI/LFM2-8B-A1B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2-8B-A1B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2-8B-A1B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-8b-a1b"},{"id":"lfm2-24b-a2b","name":"LFM2-24B-A2B","hf":"LiquidAI/LFM2-24B-A2B","org":"LiquidAI","family":"lfm","series":"LFM2","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-02-24","updated":"2026-08-05","gated":false,"params":{"total":23.844,"active":2,"src":"safetensors","q":null,"stTotal":23.844},"moe":true,"ctx":128000,"arch":{"L":40,"attn":10,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.17,"32768":0.67},"mem":{"bf16":{"w":47.69,"t":53.1},"fp8":{"w":25.33,"t":28.5},"q4":{"w":14.46,"t":16.6}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":47.69,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2-24B-A2B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"lfm2:24b-a2b","url":"https://ollama.com/library/lfm2"}],"variants":[{"id":"LiquidAI/LFM2-24B-A2B-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2-24B-A2B","kind":"main"},{"id":"LiquidAI/LFM2-24B-A2B-MLX-4bit","kind":"MLX"},{"id":"LiquidAI/LFM2-24B-A2B-MLX-8bit","kind":"MLX"},{"id":"LiquidAI/LFM2-24B-A2B-ONNX","kind":"ONNX"},{"id":"LiquidAI/LFM2-24B-A2B-MLX-bf16","kind":"MLX/BF16"},{"id":"LiquidAI/LFM2-24B-A2B-MLX-5bit","kind":"MLX"},{"id":"LiquidAI/LFM2-24B-A2B-MLX-6bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2-24B-A2B","u":"https://huggingface.co/LiquidAI/LFM2-24B-A2B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2-24B-A2B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2-24B-A2B/blob/main/LICENSE"},{"t":"Ollama library · lfm2","u":"https://ollama.com/library/lfm2"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-24b-a2b"},{"id":"lfm2-colbert-350m","name":"LFM2-ColBERT-350M","hf":"LiquidAI/LFM2-ColBERT-350M","org":"LiquidAI","family":"lfm","series":"LFM2-ColBERT","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2025-10-28","updated":"2026-08-18","gated":false,"params":{"total":0.353,"active":null,"src":"safetensors","q":null,"stTotal":0.353},"moe":false,"ctx":128000,"arch":null,"kv":null,"mem":{"bf16":{"w":0.71,"t":1.3},"fp8":{"w":0.38,"t":0.9},"q4":{"w":0.21,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.41,"native":"F32","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2-ColBERT-350M/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"LiquidAI/LFM2-ColBERT-350M","kind":"main"},{"id":"LiquidAI/LFM2-ColBERT-350M-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2-ColBERT-350M","u":"https://huggingface.co/LiquidAI/LFM2-ColBERT-350M"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2-ColBERT-350M/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2-ColBERT-350M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-colbert-350m"},{"id":"lfm2-vl-450m","name":"LFM2-VL-450M","hf":"LiquidAI/LFM2-VL-450M","org":"LiquidAI","family":"lfm","series":"LFM2-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-08-12","updated":"2026-06-29","gated":false,"params":{"total":0.451,"active":null,"src":"safetensors","q":null,"stTotal":0.451},"moe":false,"ctx":128000,"arch":{"L":16,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":0.9,"t":1.6},"fp8":{"w":0.48,"t":1.1},"q4":{"w":0.27,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.9,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2-VL-450M/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"LiquidAI/LFM2-VL-450M","kind":"main"},{"id":"LiquidAI/LFM2-VL-450M-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2-VL-450M","u":"https://huggingface.co/LiquidAI/LFM2-VL-450M"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2-VL-450M/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2-VL-450M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-vl-450m"},{"id":"lfm2-vl-1-6b","name":"LFM2-VL-1.6B","hf":"LiquidAI/LFM2-VL-1.6B","org":"LiquidAI","family":"lfm","series":"LFM2-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-08-12","updated":"2026-03-30","gated":false,"params":{"total":1.585,"active":null,"src":"safetensors","q":null,"stTotal":1.585},"moe":false,"ctx":128000,"arch":{"L":16,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":3.17,"t":4.1},"fp8":{"w":1.68,"t":2.5},"q4":{"w":0.96,"t":1.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.17,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2-VL-1.6B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"LiquidAI/LFM2-VL-1.6B-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2-VL-1.6B","kind":"main"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2-VL-1.6B","u":"https://huggingface.co/LiquidAI/LFM2-VL-1.6B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2-VL-1.6B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2-VL-1.6B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-vl-1-6b"},{"id":"lfm2-vl-3b","name":"LFM2-VL-3B","hf":"LiquidAI/LFM2-VL-3B","org":"LiquidAI","family":"lfm","series":"LFM2-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-10-22","updated":"2026-03-30","gated":false,"params":{"total":2.999,"active":null,"src":"safetensors","q":null,"stTotal":2.999},"moe":false,"ctx":128000,"arch":{"L":30,"attn":8,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.13,"32768":0.54},"mem":{"bf16":{"w":6,"t":7.2},"fp8":{"w":3.19,"t":4.1},"q4":{"w":1.82,"t":2.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2-VL-3B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"LiquidAI/LFM2-VL-3B","kind":"main"},{"id":"LiquidAI/LFM2-VL-3B-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2-VL-3B","u":"https://huggingface.co/LiquidAI/LFM2-VL-3B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2-VL-3B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2-VL-3B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-vl-3b"},{"id":"lfm2-5-230m","name":"LFM2.5-230M","hf":"LiquidAI/LFM2.5-230M","org":"LiquidAI","family":"lfm","series":"LFM2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-06-24","updated":"2026-08-19","gated":false,"params":{"total":0.23,"active":null,"src":"safetensors","q":null,"stTotal":0.23},"moe":false,"ctx":128000,"arch":{"L":14,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":0.46,"t":1.1},"fp8":{"w":0.24,"t":0.9},"q4":{"w":0.14,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.46,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-230M/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-230M-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-230M-Base","kind":"Base"},{"id":"LiquidAI/LFM2.5-230M","kind":"main"},{"id":"LiquidAI/LFM2.5-230M-ONNX","kind":"ONNX"},{"id":"LiquidAI/LFM2.5-230M-MLX-4bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-230M-MLX-8bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-230M-MLX-bf16","kind":"MLX/BF16"},{"id":"LiquidAI/LFM2.5-230M-MLX-6bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-230M-MLX-5bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-230M","u":"https://huggingface.co/LiquidAI/LFM2.5-230M"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-230M/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-230M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-230m"},{"id":"lfm2-5-350m","name":"LFM2.5-350M","hf":"LiquidAI/LFM2.5-350M","org":"LiquidAI","family":"lfm","series":"LFM2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-03-31","updated":"2026-08-05","gated":false,"params":{"total":0.354,"active":null,"src":"safetensors","q":null,"stTotal":0.354},"moe":false,"ctx":128000,"arch":{"L":16,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":0.71,"t":1.4},"fp8":{"w":0.38,"t":1},"q4":{"w":0.21,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.71,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-350M/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-350M-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-350M","kind":"main"},{"id":"LiquidAI/LFM2.5-350M-Base","kind":"Base"},{"id":"LiquidAI/LFM2.5-350M-ONNX","kind":"ONNX"},{"id":"LiquidAI/LFM2.5-350M-MLX-8bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-350M-MLX-4bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-350M-MLX-6bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-350M-MLX-bf16","kind":"MLX/BF16"},{"id":"LiquidAI/LFM2.5-350M-MLX-5bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-350M","u":"https://huggingface.co/LiquidAI/LFM2.5-350M"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-350M/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-350M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-350m"},{"id":"lfm2-5-1-2b-instruct","name":"LFM2.5-1.2B-Instruct","hf":"LiquidAI/LFM2.5-1.2B-Instruct","org":"LiquidAI","family":"lfm","series":"LFM2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-01-06","updated":"2026-08-24","gated":false,"params":{"total":1.17,"active":null,"src":"safetensors","q":null,"stTotal":1.17},"moe":false,"ctx":128000,"arch":{"L":16,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":2.34,"t":3.2},"fp8":{"w":1.24,"t":2},"q4":{"w":0.71,"t":1.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.34,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-1.2B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"LiquidAI/LFM2.5-1.2B-Instruct","kind":"Instruct"},{"id":"LiquidAI/LFM2.5-1.2B-Base","kind":"Base"},{"id":"LiquidAI/LFM2.5-1.2B-Instruct-ONNX","kind":"Instruct/ONNX"},{"id":"LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit","kind":"Instruct/MLX"},{"id":"LiquidAI/LFM2.5-1.2B-Base-GGUF","kind":"Base/GGUF"},{"id":"LiquidAI/LFM2.5-1.2B-Instruct-MLX-8bit","kind":"Instruct/MLX"},{"id":"LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16","kind":"Instruct/MLX/BF16"},{"id":"LiquidAI/LFM2.5-1.2B-Instruct-MLX-6bit","kind":"Instruct/MLX"},{"id":"LiquidAI/LFM2.5-1.2B-Instruct-MLX-5bit","kind":"Instruct/MLX"},{"id":"LiquidAI/LFM2.5-1.2B-Base-ONNX","kind":"Base/ONNX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-1.2B-Instruct","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-1-2b-instruct"},{"id":"lfm2-5-2-6b","name":"LFM2.5-2.6B","hf":"LiquidAI/LFM2.5-2.6B","org":"LiquidAI","family":"lfm","series":"LFM2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-07-28","updated":"2026-08-24","gated":false,"params":{"total":2.697,"active":null,"src":"safetensors","q":null,"stTotal":2.697},"moe":false,"ctx":131072,"arch":{"L":30,"attn":8,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.13,"32768":0.54,"131072":2.15},"mem":{"bf16":{"w":5.39,"t":6.6},"fp8":{"w":2.87,"t":3.8},"q4":{"w":1.64,"t":2.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.39,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-2.6B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-2.6B-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-2.6B","kind":"main"},{"id":"LiquidAI/LFM2.5-2.6B-MLX-8bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-2.6B-Base","kind":"Base"},{"id":"LiquidAI/LFM2.5-2.6B-MLX-4bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-2.6B-ONNX","kind":"ONNX"},{"id":"LiquidAI/LFM2.5-2.6B-MLX-bf16","kind":"MLX/BF16"},{"id":"LiquidAI/LFM2.5-2.6B-MLX-6bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-2.6B-MLX-mxfp4","kind":"MLX/MXFP4"},{"id":"LiquidAI/LFM2.5-2.6B-MLX-nvfp4","kind":"MLX/NVFP4"},{"id":"LiquidAI/LFM2.5-2.6B-MLX-mxfp8","kind":"MLX"},{"id":"LiquidAI/LFM2.5-2.6B-MLX-5bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-2.6B-MLX","kind":"MLX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-2.6B","u":"https://huggingface.co/LiquidAI/LFM2.5-2.6B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-2.6B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-2.6B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-2-6b"},{"id":"lfm2-5-8b-a1b","name":"LFM2.5-8B-A1B","hf":"LiquidAI/LFM2.5-8B-A1B","org":"LiquidAI","family":"lfm","series":"LFM2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-05-28","updated":"2026-08-24","gated":false,"params":{"total":8.468,"active":1,"src":"safetensors","q":null,"stTotal":8.468},"moe":true,"ctx":128000,"arch":{"L":24,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":16.94,"t":19.2},"fp8":{"w":9,"t":10.5},"q4":{"w":5.13,"t":6.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.94,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-8B-A1B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-8B-A1B-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-8B-A1B","kind":"main"},{"id":"LiquidAI/LFM2.5-8B-A1B-MLX-4bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-8B-A1B-Base","kind":"Base"},{"id":"LiquidAI/LFM2.5-8B-A1B-MLX-8bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-8B-A1B-MLX-6bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-8B-A1B-MLX-bf16","kind":"MLX/BF16"},{"id":"LiquidAI/LFM2.5-8B-A1B-MLX-5bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-8B-A1B-ONNX","kind":"ONNX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-8B-A1B","u":"https://huggingface.co/LiquidAI/LFM2.5-8B-A1B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-8B-A1B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-8B-A1B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-8b-a1b"},{"id":"lfm2-5-24b-a2b","name":"LFM2.5-24B-A2B","hf":"LiquidAI/LFM2.5-24B-A2B","org":"LiquidAI","family":"lfm","series":"LFM2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-10-12","updated":"2026-10-21","gated":false,"params":{"total":23.972,"active":2,"src":"safetensors","q":null,"stTotal":23.972},"moe":true,"ctx":131072,"arch":{"L":40,"attn":10,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.17,"32768":0.67,"131072":2.68},"mem":{"bf16":{"w":47.94,"t":53.4},"fp8":{"w":25.47,"t":28.7},"q4":{"w":14.53,"t":16.7}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":47.94,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-24B-A2B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-24B-A2B-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-24B-A2B-FP8","kind":"FP8"},{"id":"LiquidAI/LFM2.5-24B-A2B","kind":"main"},{"id":"LiquidAI/LFM2.5-24B-A2B-MLX-4bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-24B-A2B-MLX-8bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-24B-A2B-MLX-5bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-24B-A2B-Base","kind":"Base"},{"id":"LiquidAI/LFM2.5-24B-A2B-MLX-6bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-24B-A2B-MLX-bf16","kind":"MLX/BF16"},{"id":"LiquidAI/LFM2.5-24B-A2B-ONNX","kind":"ONNX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-24B-A2B","u":"https://huggingface.co/LiquidAI/LFM2.5-24B-A2B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-24B-A2B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-24B-A2B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/lfm2-5-24b-a2b/"},{"id":"lfm2-5-audio-1-5b","name":"LFM2.5-Audio-1.5B","hf":"LiquidAI/LFM2.5-Audio-1.5B","org":"LiquidAI","family":"lfm","series":"LFM2.5-Audio","task":"tts","pipeline":"audio-to-audio","tags":[],"released":"2025-12-18","updated":"2026-03-30","gated":false,"params":{"total":1.47,"active":null,"src":"safetensors","q":null,"stTotal":1.47},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":2.94,"t":3.7},"fp8":{"w":1.56,"t":2.2},"q4":{"w":0.89,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.33,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"llamacpp","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-Audio-1.5B-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-Audio-1.5B","kind":"main"},{"id":"LiquidAI/LFM2.5-Audio-1.5B-ONNX","kind":"ONNX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-Audio-1.5B","u":"https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-audio-1-5b"},{"id":"lfm2-5-colbert-350m","name":"LFM2.5-ColBERT-350M","hf":"LiquidAI/LFM2.5-ColBERT-350M","org":"LiquidAI","family":"lfm","series":"LFM2.5-ColBERT","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2026-05-20","updated":"2026-08-17","gated":false,"params":{"total":0.353,"active":null,"src":"safetensors","q":null,"stTotal":0.353},"moe":false,"ctx":128000,"arch":null,"kv":null,"mem":{"bf16":{"w":0.71,"t":1.3},"fp8":{"w":0.38,"t":0.9},"q4":{"w":0.21,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.71,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-ColBERT-350M/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-ColBERT-350M","kind":"main"},{"id":"LiquidAI/LFM2.5-ColBERT-350M-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-ColBERT-350M","u":"https://huggingface.co/LiquidAI/LFM2.5-ColBERT-350M"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-ColBERT-350M/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-ColBERT-350M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-colbert-350m"},{"id":"lfm2-5-embedding-350m","name":"LFM2.5-Embedding-350M","hf":"LiquidAI/LFM2.5-Embedding-350M","org":"LiquidAI","family":"lfm","series":"LFM2.5-Embedding","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2026-05-05","updated":"2026-06-20","gated":false,"params":{"total":0.354,"active":null,"src":"safetensors","q":null,"stTotal":0.354},"moe":false,"ctx":128000,"arch":null,"kv":null,"mem":{"bf16":{"w":0.71,"t":1.3},"fp8":{"w":0.38,"t":0.9},"q4":{"w":0.21,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.71,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-Embedding-350M","kind":"main"},{"id":"LiquidAI/LFM2.5-Embedding-350M-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-Embedding-350M","u":"https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-embedding-350m"},{"id":"lfm2-5-encoder-350m-diffusion","name":"LFM2.5-Encoder-350M-Diffusion","hf":"LiquidAI/LFM2.5-Encoder-350M-Diffusion","org":"LiquidAI","family":"lfm","series":"LFM2.5-Encoder-Diffusion","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2026-07-10","updated":"2026-07-28","gated":false,"params":{"total":0.354,"active":null,"src":"safetensors","q":null,"stTotal":0.354},"moe":false,"ctx":128000,"arch":{"L":16,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":0.71,"t":1.4},"fp8":{"w":0.38,"t":1},"q4":{"w":0.21,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.42,"native":"F32","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-Encoder-350M-Diffusion/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-Encoder-350M-Diffusion","kind":"main"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-Encoder-350M-Diffusion","u":"https://huggingface.co/LiquidAI/LFM2.5-Encoder-350M-Diffusion"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-Encoder-350M-Diffusion/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-Encoder-350M-Diffusion/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-encoder-350m-diffusion"},{"id":"lfm2-5-1-2b-jp","name":"LFM2.5-1.2B-JP","hf":"LiquidAI/LFM2.5-1.2B-JP","org":"LiquidAI","family":"lfm","series":"LFM2.5-JP","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-01-04","updated":"2026-06-13","gated":false,"params":{"total":1.17,"active":null,"src":"safetensors","q":null,"stTotal":1.17},"moe":false,"ctx":128000,"arch":{"L":16,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":2.34,"t":3.2},"fp8":{"w":1.24,"t":2},"q4":{"w":0.71,"t":1.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.34,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"LiquidAI/LFM2.5-1.2B-JP-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-1.2B-JP","kind":"main"},{"id":"LiquidAI/LFM2.5-1.2B-JP-MLX-4bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-1.2B-JP-MLX-8bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-1.2B-JP-MLX-5bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-1.2B-JP-MLX-bf16","kind":"MLX/BF16"},{"id":"LiquidAI/LFM2.5-1.2B-JP-MLX-6bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-1.2B-JP-ONNX","kind":"ONNX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-1.2B-JP","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-1-2b-jp"},{"id":"lfm2-5-1-2b-jp-202606","name":"LFM2.5-1.2B-JP-202606","hf":"LiquidAI/LFM2.5-1.2B-JP-202606","org":"LiquidAI","family":"lfm","series":"LFM2.5-JP-202606","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-05-26","updated":"2026-06-04","gated":false,"params":{"total":1.17,"active":null,"src":"safetensors","q":null,"stTotal":1.17},"moe":false,"ctx":128000,"arch":{"L":16,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":2.34,"t":3.2},"fp8":{"w":1.24,"t":2},"q4":{"w":0.71,"t":1.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.34,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP-202606/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-1.2B-JP-202606-ONNX","kind":"ONNX"},{"id":"LiquidAI/LFM2.5-1.2B-JP-202606","kind":"main"},{"id":"LiquidAI/LFM2.5-1.2B-JP-202606-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-1.2B-JP-202606-MLX-4bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-1.2B-JP-202606-MLX-8bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-1.2B-JP-202606-MLX-6bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-1.2B-JP-202606-MLX-5bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-1.2B-JP-202606","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP-202606"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP-202606/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP-202606/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-1-2b-jp-202606"},{"id":"lfm2-5-1-2b-thinking","name":"LFM2.5-1.2B-Thinking","hf":"LiquidAI/LFM2.5-1.2B-Thinking","org":"LiquidAI","family":"lfm","series":"LFM2.5-Thinking","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2026-01-20","updated":"2026-08-05","gated":false,"params":{"total":1.17,"active":null,"src":"safetensors","q":null,"stTotal":1.17},"moe":false,"ctx":128000,"arch":{"L":16,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":2.34,"t":3.2},"fp8":{"w":1.24,"t":2},"q4":{"w":0.71,"t":1.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.34,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-1.2B-Thinking-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-1.2B-Thinking","kind":"main"},{"id":"LiquidAI/LFM2.5-1.2B-Thinking-ONNX","kind":"ONNX"},{"id":"LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16","kind":"MLX/BF16"},{"id":"LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-1.2B-Thinking","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-1-2b-thinking"},{"id":"lfm2-5-vl-450m","name":"LFM2.5-VL-450M","hf":"LiquidAI/LFM2.5-VL-450M","org":"LiquidAI","family":"lfm","series":"LFM2.5-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-04-08","updated":"2026-04-08","gated":false,"params":{"total":0.449,"active":null,"src":"safetensors","q":null,"stTotal":0.449},"moe":false,"ctx":128000,"arch":{"L":16,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":0.9,"t":1.6},"fp8":{"w":0.48,"t":1.1},"q4":{"w":0.27,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.9,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-VL-450M/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-VL-450M","kind":"main"},{"id":"LiquidAI/LFM2.5-VL-450M-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-VL-450M-MLX-4bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-VL-450M-ONNX","kind":"ONNX"},{"id":"LiquidAI/LFM2.5-VL-450M-MLX-8bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-VL-450M-MLX-bf16","kind":"MLX/BF16"},{"id":"LiquidAI/LFM2.5-VL-450M-MLX-6bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-VL-450M-MLX-5bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-VL-450M","u":"https://huggingface.co/LiquidAI/LFM2.5-VL-450M"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-VL-450M/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-VL-450M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-vl-450m"},{"id":"lfm2-5-vl-1-6b","name":"LFM2.5-VL-1.6B","hf":"LiquidAI/LFM2.5-VL-1.6B","org":"LiquidAI","family":"lfm","series":"LFM2.5-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-01-05","updated":"2026-03-30","gated":false,"params":{"total":1.597,"active":null,"src":"safetensors","q":null,"stTotal":1.597},"moe":false,"ctx":128000,"arch":{"L":16,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":3.19,"t":4.1},"fp8":{"w":1.7,"t":2.5},"q4":{"w":0.97,"t":1.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.19,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-VL-1.6B-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-VL-1.6B","kind":"main"},{"id":"LiquidAI/LFM2.5-VL-1.6B-ONNX","kind":"ONNX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-VL-1.6B","u":"https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-vl-1-6b"},{"id":"lfm2-5-vl-3b","name":"LFM2.5-VL-3B","hf":"LiquidAI/LFM2.5-VL-3B","org":"LiquidAI","family":"lfm","series":"LFM2.5-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-08-11","updated":"2026-09-24","gated":false,"params":{"total":3.123,"active":null,"src":"safetensors","q":null,"stTotal":3.123},"moe":false,"ctx":32768,"arch":{"L":30,"attn":8,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.13,"32768":0.54},"mem":{"bf16":{"w":6.25,"t":7.5},"fp8":{"w":3.32,"t":4.3},"q4":{"w":1.89,"t":2.7}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.25,"native":"BF16","license":{"id":"lfm1.0","name":"lfm1.0","link":"https://huggingface.co/LiquidAI/LFM2.5-VL-3B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"LiquidAI/LFM2.5-VL-3B-GGUF","kind":"GGUF"},{"id":"LiquidAI/LFM2.5-VL-3B","kind":"main"},{"id":"LiquidAI/LFM2.5-VL-3B-MLX-4bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-VL-3B-ONNX","kind":"ONNX"},{"id":"LiquidAI/LFM2.5-VL-3B-MLX-8bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-VL-3B-MLX-bf16","kind":"MLX/BF16"},{"id":"LiquidAI/LFM2.5-VL-3B-MLX-6bit","kind":"MLX"},{"id":"LiquidAI/LFM2.5-VL-3B-MLX-5bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · LiquidAI/LFM2.5-VL-3B","u":"https://huggingface.co/LiquidAI/LFM2.5-VL-3B"},{"t":"config.json","u":"https://huggingface.co/LiquidAI/LFM2.5-VL-3B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/LiquidAI/LFM2.5-VL-3B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/lfm/#m-lfm2-5-vl-3b"},{"id":"ling-1t","name":"Ling-1T","hf":"inclusionAI/Ling-1T","org":"inclusionAI","family":"ling","series":"Ling","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-10-02","updated":"2026-09-24","gated":false,"params":{"total":1000,"active":50,"src":"card","q":"1T total / 50B active parameters","stTotal":999.705},"moe":true,"ctx":32768,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74},"mem":{"bf16":{"w":2000,"t":2203.2},"fp8":{"w":1062.5,"t":1171.9},"q4":{"w":606.25,"t":670.1}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":1999.42,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ling-1T","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-1T","u":"https://huggingface.co/inclusionAI/Ling-1T"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-1T/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ling-1t/"},{"id":"ling-2-5-1t","name":"Ling-2.5-1T","hf":"inclusionAI/Ling-2.5-1T","org":"inclusionAI","family":"ling","series":"Ling-2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-02-14","updated":"2026-09-24","gated":false,"params":{"total":1000,"active":63,"src":"card","q":"Ling-2.5-1T features 1T total parameters (with 63B active parameters).","stTotal":1012.231},"moe":true,"ctx":131072,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.75,"32768":3.02,"131072":12.08},"mem":{"bf16":{"w":2000,"t":2201.2},"fp8":{"w":1062.5,"t":1170},"q4":{"w":606.25,"t":668.1}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":2024.47,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ling-2.5-1T","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-2.5-1T","u":"https://huggingface.co/inclusionAI/Ling-2.5-1T"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-2.5-1T/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ling-2-5-1t/"},{"id":"ling-2-6-1t","name":"Ling-2.6-1T","hf":"inclusionAI/Ling-2.6-1T","org":"inclusionAI","family":"ling","series":"Ling-2.6","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-29","updated":"2026-09-24","gated":false,"params":{"total":1025.414,"active":null,"src":"safetensors","q":null,"stTotal":1025.414},"moe":true,"ctx":262144,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.75,"32768":3.02,"131072":12.08},"mem":{"bf16":{"w":2050.83,"t":2257.2},"fp8":{"w":1089.5,"t":1199.7},"q4":{"w":621.66,"t":685.1}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":1041.84,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ling-2.6-1T","kind":"main"},{"id":"inclusionAI/Ling-2.6-1T-base","kind":"Base"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-2.6-1T","u":"https://huggingface.co/inclusionAI/Ling-2.6-1T"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-2.6-1T/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ling-2-6-1t/"},{"id":"ling-2-6-flash","name":"Ling-2.6-flash","hf":"inclusionAI/Ling-2.6-flash","org":"inclusionAI","family":"ling","series":"Ling-2.6-flash","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-28","updated":"2026-09-24","gated":false,"params":{"total":104,"active":7.4,"src":"card","q":"104B total parameters and 7.4B active parameters","stTotal":107.494},"moe":true,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.3,"32768":1.21,"131072":4.83},"mem":{"bf16":{"w":208,"t":229.6},"fp8":{"w":110.5,"t":122.4},"q4":{"w":63.05,"t":70.2}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"h100","mac":"mac128"}},"disk":214.99,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"}],"variants":[{"id":"inclusionAI/Ling-2.6-flash","kind":"main"},{"id":"inclusionAI/Ling-2.6-flash-base","kind":"Base"},{"id":"inclusionAI/Ling-2.6-flash-int4","kind":"INT4"},{"id":"inclusionAI/Ling-2.6-flash-fp8","kind":"FP8"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-2.6-flash","u":"https://huggingface.co/inclusionAI/Ling-2.6-flash"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-2.6-flash/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ling-2-6-flash/"},{"id":"ling-3-0-flash","name":"Ling-3.0-flash","hf":"inclusionAI/Ling-3.0-flash","org":"inclusionAI","family":"ling","series":"Ling-3.0-flash","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-08-02","updated":"2026-10-12","gated":false,"params":{"total":124,"active":5.1,"src":"card","q":"Total 124B, Activated 5.1B","stTotal":127.486},"moe":true,"ctx":262144,"arch":{"L":42,"attn":42,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.4,"32768":1.59,"131072":6.34},"mem":{"bf16":{"w":248,"t":273.7},"fp8":{"w":131.75,"t":145.8},"q4":{"w":75.17,"t":83.6}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":254.98,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"inclusionAI/Ling-3.0-flash","kind":"main"},{"id":"inclusionAI/Ling-3.0-flash-fp4","kind":"FP4"},{"id":"inclusionAI/Ling-3.0-flash-GGUF","kind":"GGUF"},{"id":"inclusionAI/Ling-3.0-flash-int4","kind":"INT4"},{"id":"inclusionAI/Ling-3.0-flash-fp8","kind":"FP8"},{"id":"inclusionAI/Ling-3.0-flash-base","kind":"Base"},{"id":"inclusionAI/Ling-3.0-flash-Fin-fp4","kind":"FP4"},{"id":"inclusionAI/Ling-3.0-flash-Fin-fp8","kind":"FP8"},{"id":"inclusionAI/Ling-3.0-flash-Fin-int4","kind":"INT4"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-3.0-flash","u":"https://huggingface.co/inclusionAI/Ling-3.0-flash"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-3.0-flash/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ling-3-0-flash/"},{"id":"ling-3-0-flash-ubtree","name":"Ling-3.0-flash-UBTree","hf":"inclusionAI/Ling-3.0-flash-UBTree","org":"inclusionAI","family":"ling","series":"Ling-3.0-flash-UBTree","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-10-14","updated":"2026-10-21","gated":false,"params":{"total":0.482,"active":null,"src":"safetensors","q":null,"stTotal":0.482},"moe":false,"ctx":131072,"arch":{"L":5,"attn":5,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.67,"32768":2.68,"131072":10.74},"mem":{"bf16":{"w":0.96,"t":2.2},"fp8":{"w":0.51,"t":1.7},"q4":{"w":0.29,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.96,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"sglang","via":"card"}],"variants":[{"id":"inclusionAI/Ling-3.0-flash-UBTree","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-3.0-flash-UBTree","u":"https://huggingface.co/inclusionAI/Ling-3.0-flash-UBTree"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-3.0-flash-UBTree/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ling-3-0-flash-ubtree/"},{"id":"ling-3-0-flash-vl","name":"Ling-3.0-flash-VL","hf":"inclusionAI/Ling-3.0-flash-VL","org":"inclusionAI","family":"ling","series":"Ling-3.0-flash-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-09-04","updated":"2026-09-24","gated":false,"params":{"total":124,"active":5.5,"src":"card","q":"124B total parameters, only 5.5B activated parameters per token","stTotal":124.848},"moe":true,"ctx":131072,"arch":{"L":42,"attn":42,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.4,"32768":1.59,"131072":6.34},"mem":{"bf16":{"w":248,"t":273.7},"fp8":{"w":131.75,"t":145.8},"q4":{"w":75.17,"t":83.6}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":249.71,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"}],"variants":[{"id":"inclusionAI/Ling-3.0-flash-VL","kind":"main"},{"id":"inclusionAI/Ling-3.0-flash-VL-int4","kind":"INT4"},{"id":"inclusionAI/Ling-3.0-flash-VL-fp4","kind":"FP4"},{"id":"inclusionAI/Ling-3.0-flash-VL-fp8","kind":"FP8"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-3.0-flash-VL","u":"https://huggingface.co/inclusionAI/Ling-3.0-flash-VL"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-3.0-flash-VL/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ling-3-0-flash-vl/"},{"id":"ling-3-0-tiny","name":"Ling-3.0-tiny","hf":"inclusionAI/Ling-3.0-tiny","org":"inclusionAI","family":"ling","series":"Ling-3.0-tiny","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-08-10","updated":"2026-09-24","gated":false,"params":{"total":7.9,"active":1.3,"src":"card","q":"7.9B total parameters and only 1.3B activated parameters per token","stTotal":7.893},"moe":true,"ctx":131072,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.23,"32768":0.91,"131072":3.62},"mem":{"bf16":{"w":15.8,"t":18.1},"fp8":{"w":8.39,"t":10},"q4":{"w":4.79,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.79,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"ollama","via":"card"},{"id":"mlx","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"inclusionAI/Ling-3.0-tiny-GGUF","kind":"GGUF"},{"id":"inclusionAI/Ling-3.0-tiny","kind":"main"},{"id":"inclusionAI/Ling-3.0-tiny-int4","kind":"INT4"},{"id":"inclusionAI/Ling-3.0-tiny-fp8","kind":"FP8"},{"id":"inclusionAI/Ling-3.0-tiny-base","kind":"Base"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-3.0-tiny","u":"https://huggingface.co/inclusionAI/Ling-3.0-tiny"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-3.0-tiny/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ling/#m-ling-3-0-tiny"},{"id":"ling-3-0-tiny-ubtree","name":"Ling-3.0-tiny-UBTree","hf":"inclusionAI/Ling-3.0-tiny-UBTree","org":"inclusionAI","family":"ling","series":"Ling-3.0-tiny-UBTree","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-10-21","updated":"2026-10-21","gated":false,"params":{"total":0.183,"active":null,"src":"safetensors","q":null,"stTotal":0.183},"moe":false,"ctx":131072,"arch":{"L":5,"attn":5,"slide":0,"win":null,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.34,"32768":1.34,"131072":5.37},"mem":{"bf16":{"w":0.37,"t":1.2},"fp8":{"w":0.19,"t":1.1},"q4":{"w":0.11,"t":1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.37,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"sglang","via":"card"}],"variants":[{"id":"inclusionAI/Ling-3.0-tiny-UBTree","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-3.0-tiny-UBTree","u":"https://huggingface.co/inclusionAI/Ling-3.0-tiny-UBTree"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-3.0-tiny-UBTree/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ling-3-0-tiny-ubtree/"},{"id":"ling-3-1-flash","name":"Ling-3.1-flash","hf":"inclusionAI/Ling-3.1-flash","org":"inclusionAI","family":"ling","series":"Ling-3.1-flash","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-10-13","updated":"2026-10-20","gated":false,"params":{"total":560,"active":25,"src":"card","q":"Total 560B, Activated 25B","stTotal":572.121},"moe":true,"ctx":262144,"arch":{"L":72,"attn":72,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.68,"32768":2.72,"131072":10.87},"mem":{"bf16":{"w":1120,"t":1233.2},"fp8":{"w":595,"t":655.7},"q4":{"w":339.5,"t":374.6}},"fits":{"bf16":{"gpu":"8xb200","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":573.78,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"}],"variants":[{"id":"inclusionAI/Ling-3.1-flash","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-3.1-flash","u":"https://huggingface.co/inclusionAI/Ling-3.1-flash"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-3.1-flash/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ling-3-1-flash/"},{"id":"ling-flash-2-0","name":"Ling-flash-2.0","hf":"inclusionAI/Ling-flash-2.0","org":"inclusionAI","family":"ling","series":"Ling-flash-2.0","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-17","updated":"2026-09-24","gated":false,"params":{"total":100,"active":6.1,"src":"card","q":"a language model with 100B total parameters and 6.1B activated parameters","stTotal":102.89},"moe":true,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54,"32768":2.15},"mem":{"bf16":{"w":200,"t":221},"fp8":{"w":106.25,"t":117.9},"q4":{"w":60.62,"t":67.7}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"h100","mac":"mac128"}},"disk":205.78,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ling-flash-2.0","kind":"main"},{"id":"inclusionAI/Ling-flash-base-2.0","kind":"Base"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-flash-2.0","u":"https://huggingface.co/inclusionAI/Ling-flash-2.0"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-flash-2.0/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ling-flash-2-0/"},{"id":"ling-lite","name":"Ling-lite","hf":"inclusionAI/Ling-lite","org":"inclusionAI","family":"ling","series":"Ling-lite","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-02-28","updated":"2025-05-08","gated":false,"params":{"total":16.8,"active":2.75,"src":"card","q":"16.8 billion parameters with 2.75 billion activated parameters","stTotal":16.802},"moe":true,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":33.6,"t":37.9},"fp8":{"w":17.85,"t":20.6},"q4":{"w":10.19,"t":12.2}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":33.6,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/inclusionAI/Ling-lite/blob/main/LICENCE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ling-lite","kind":"main"},{"id":"inclusionAI/Ming-Lite-Omni","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-lite","u":"https://huggingface.co/inclusionAI/Ling-lite"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-lite/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/inclusionAI/Ling-lite/blob/main/LICENCE"}],"page":"https://aimap.page/en/models/compute/open-models/family/ling/#m-ling-lite"},{"id":"ling-lite-1-5","name":"Ling-lite-1.5","hf":"inclusionAI/Ling-lite-1.5","org":"inclusionAI","family":"ling","series":"Ling-lite-1.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-05-11","updated":"2026-04-13","gated":false,"params":{"total":16.8,"active":2.75,"src":"card","q":"16.8 billion parameters with 2.75 billion activated parameters","stTotal":16.802},"moe":true,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":33.6,"t":37.9},"fp8":{"w":17.85,"t":20.6},"q4":{"w":10.19,"t":12.2}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":33.6,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/inclusionAI/Ling-lite-1.5/blob/main/LICENCE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ling-lite-1.5","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-lite-1.5","u":"https://huggingface.co/inclusionAI/Ling-lite-1.5"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-lite-1.5/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/inclusionAI/Ling-lite-1.5/blob/main/LICENCE"}],"page":"https://aimap.page/en/models/compute/open-models/family/ling/#m-ling-lite-1-5"},{"id":"ling-mini-2-0","name":"Ling-mini-2.0","hf":"inclusionAI/Ling-mini-2.0","org":"inclusionAI","family":"ling","series":"Ling-mini-2.0","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-08","updated":"2026-09-24","gated":false,"params":{"total":16.26,"active":1.43,"src":"card","q":"1.43B activated of 16.26B total params","stTotal":16.256},"moe":true,"ctx":32768,"arch":{"L":20,"attn":20,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.34,"32768":1.34},"mem":{"bf16":{"w":32.52,"t":36.6},"fp8":{"w":17.28,"t":19.8},"q4":{"w":9.86,"t":11.7}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":32.51,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"inclusionAI/Ling-mini-2.0","kind":"main"},{"id":"inclusionAI/Ling-mini-2.0-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-mini-2.0","u":"https://huggingface.co/inclusionAI/Ling-mini-2.0"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-mini-2.0/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ling/#m-ling-mini-2-0"},{"id":"ling-plus","name":"Ling-plus","hf":"inclusionAI/Ling-plus","org":"inclusionAI","family":"ling","series":"Ling-plus","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-02-28","updated":"2025-04-14","gated":false,"params":{"total":290,"active":28.8,"src":"card","q":"| Ling-plus | 290B | 28.8B | 64K |","stTotal":292.541},"moe":true,"ctx":16384,"arch":{"L":88,"attn":88,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.95},"mem":{"bf16":{"w":580,"t":641.5},"fp8":{"w":308.12,"t":342.4},"q4":{"w":175.81,"t":196.8}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":585.08,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/inclusionAI/Ling-plus/blob/main/LICENCE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ling-plus","kind":"main"},{"id":"inclusionAI/Ling-plus-base","kind":"Base"}],"sources":[{"t":"Hugging Face · inclusionAI/Ling-plus","u":"https://huggingface.co/inclusionAI/Ling-plus"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ling-plus/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/inclusionAI/Ling-plus/blob/main/LICENCE"}],"page":"https://aimap.page/en/models/compute/open-models/ling-plus/"},{"id":"ming-3-0-asr-tiny","name":"Ming-3.0-asr-tiny","hf":"inclusionAI/Ming-3.0-asr-tiny","org":"inclusionAI","family":"ling","series":"Ming-3.0-asr-tiny","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-10-14","updated":"2026-10-21","gated":false,"params":{"total":8.866,"active":null,"src":"safetensors","q":null,"stTotal":8.866},"moe":true,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":17.73,"t":20},"fp8":{"w":9.42,"t":10.9},"q4":{"w":5.38,"t":6.4}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.73,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/inclusionAI/Ming-3.0-asr-tiny/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ming-3.0-asr-tiny","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ming-3.0-asr-tiny","u":"https://huggingface.co/inclusionAI/Ming-3.0-asr-tiny"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ming-3.0-asr-tiny/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/inclusionAI/Ming-3.0-asr-tiny/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/ming-3-0-asr-tiny/"},{"id":"ming-3-0-audio-flash","name":"Ming-3.0-audio-flash","hf":"inclusionAI/Ming-3.0-audio-flash","org":"inclusionAI","family":"ling","series":"Ming-3.0-audio-flash","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2026-09-03","updated":"2026-10-22","gated":false,"params":{"total":126,"active":6.5,"src":"card","q":"126B total parameters, 6.5B activated per inference step","stTotal":128.181},"moe":true,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":252,"t":277.7},"fp8":{"w":133.88,"t":147.8},"q4":{"w":76.39,"t":84.5}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":256.37,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/inclusionAI/Ming-3.0-audio-flash/blob/main/talker/data/lid.176.LICENSE.md","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ming-3.0-audio-flash","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ming-3.0-audio-flash","u":"https://huggingface.co/inclusionAI/Ming-3.0-audio-flash"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ming-3.0-audio-flash/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/inclusionAI/Ming-3.0-audio-flash/blob/main/talker/data/lid.176.LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/ming-3-0-audio-flash/"},{"id":"ming-3-0-tts-0-5b","name":"Ming-3.0-tts-0.5B","hf":"inclusionAI/Ming-3.0-tts-0.5B","org":"inclusionAI","family":"ling","series":"Ming-3.0-tts","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2026-09-22","updated":"2026-10-21","gated":false,"params":{"total":1.479,"active":null,"src":"safetensors","q":null,"stTotal":1.479},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":2.96,"t":3.8},"fp8":{"w":1.57,"t":2.2},"q4":{"w":0.9,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.96,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ming-3.0-tts-0.5B","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ming-3.0-tts-0.5B","u":"https://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ming-3.0-tts-0.5B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ming-3-0-tts-0-5b/"},{"id":"ming-3-0-tts-tiny","name":"Ming-3.0-tts-tiny","hf":"inclusionAI/Ming-3.0-tts-tiny","org":"inclusionAI","family":"ling","series":"Ming-3.0-tts-tiny","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2026-09-22","updated":"2026-10-21","gated":false,"params":{"total":8.981,"active":1.3,"src":"safetensors","q":"7.9B-A1.3B multilingual MoE speech synthesis … activates about 1.3B parameters per token","stTotal":8.981},"moe":true,"ctx":4096,"arch":null,"kv":null,"mem":{"bf16":{"w":17.96,"t":20.3},"fp8":{"w":9.54,"t":11},"q4":{"w":5.44,"t":6.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.96,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ming-3.0-tts-tiny","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ming-3.0-tts-tiny","u":"https://huggingface.co/inclusionAI/Ming-3.0-tts-tiny"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ming-3.0-tts-tiny/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ming-3-0-tts-tiny/"},{"id":"ming-image-0-1-design","name":"Ming-Image-0.1-Design","hf":"inclusionAI/Ming-Image-0.1-Design","org":"inclusionAI","family":"ling","series":"Ming-Image-0.1-Design","task":"image","pipeline":"text-to-image","tags":[],"released":"2026-09-17","updated":"2026-10-14","gated":false,"params":{"total":6.155,"active":null,"src":"safetensors","q":null,"stTotal":6.155},"moe":true,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":12.31,"t":14},"fp8":{"w":6.54,"t":7.7},"q4":{"w":3.73,"t":4.6}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":52.87,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/inclusionAI/Ming-Image-0.1-Design/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"}],"variants":[{"id":"inclusionAI/Ming-Image-0.1-Design","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ming-Image-0.1-Design","u":"https://huggingface.co/inclusionAI/Ming-Image-0.1-Design"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ming-Image-0.1-Design/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/inclusionAI/Ming-Image-0.1-Design/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/ming-image-0-1-design/"},{"id":"ming-flash-omni-2-0","name":"Ming-flash-omni-2.0","hf":"inclusionAI/Ming-flash-omni-2.0","org":"inclusionAI","family":"ling","series":"Ming-flash-omni-2.0","task":"omni","pipeline":"any-to-any","tags":[],"released":"2026-02-10","updated":"2026-09-29","gated":false,"params":{"total":100,"active":6,"src":"card","q":"100B total and 6B active parameters","stTotal":104.232},"moe":true,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54,"32768":2.15},"mem":{"bf16":{"w":200,"t":221},"fp8":{"w":106.25,"t":117.9},"q4":{"w":60.62,"t":67.7}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"h100","mac":"mac128"}},"disk":208.51,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"hf-library"}],"variants":[{"id":"inclusionAI/Ming-flash-omni-2.0","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ming-flash-omni-2.0","u":"https://huggingface.co/inclusionAI/Ming-flash-omni-2.0"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ming-flash-omni-2.0/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ming-flash-omni-2-0/"},{"id":"ming-flash-omni-preview","name":"Ming-flash-omni-Preview","hf":"inclusionAI/Ming-flash-omni-Preview","org":"inclusionAI","family":"ling","series":"Ming-flash-omni-Preview","task":"omni","pipeline":"any-to-any","tags":[],"released":"2025-10-14","updated":"2026-09-24","gated":false,"params":{"total":104.377,"active":6,"src":"safetensors","q":"a 100B-A6B MoE backbone (an extension of Ling-Flash-2.0)","stTotal":104.377},"moe":true,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54,"32768":2.15},"mem":{"bf16":{"w":208.75,"t":230.7},"fp8":{"w":110.9,"t":123},"q4":{"w":63.28,"t":70.6}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"h100","mac":"mac128"}},"disk":208.8,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"hf-library"}],"variants":[{"id":"inclusionAI/Ming-flash-omni-Preview","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ming-flash-omni-Preview","u":"https://huggingface.co/inclusionAI/Ming-flash-omni-Preview"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ming-flash-omni-Preview/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ming-flash-omni-preview/"},{"id":"ming-omni-tts-0-5b","name":"Ming-omni-tts-0.5B","hf":"inclusionAI/Ming-omni-tts-0.5B","org":"inclusionAI","family":"ling","series":"Ming-omni-tts","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2026-02-11","updated":"2026-02-25","gated":false,"params":{"total":1.616,"active":null,"src":"safetensors","q":null,"stTotal":1.616},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":3.23,"t":4.1},"fp8":{"w":1.72,"t":2.4},"q4":{"w":0.98,"t":1.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.23,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"inclusionAI/Ming-omni-tts-0.5B","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ming-omni-tts-0.5B","u":"https://huggingface.co/inclusionAI/Ming-omni-tts-0.5B"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ming-omni-tts-0.5B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ling/#m-ming-omni-tts-0-5b"},{"id":"ring-1t","name":"Ring-1T","hf":"inclusionAI/Ring-1T","org":"inclusionAI","family":"ling","series":"Ring","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-10-10","updated":"2026-09-24","gated":false,"params":{"total":1000,"active":50,"src":"card","q":"contains 1 trillion total parameters with 50 billion activated parameters","stTotal":999.705},"moe":true,"ctx":65536,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74},"mem":{"bf16":{"w":2000,"t":2203.2},"fp8":{"w":1062.5,"t":1171.9},"q4":{"w":606.25,"t":670.1}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":1999.42,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ring-1T","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ring-1T","u":"https://huggingface.co/inclusionAI/Ring-1T"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ring-1T/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ring-1t/"},{"id":"ring-2-5-1t","name":"Ring-2.5-1T","hf":"inclusionAI/Ring-2.5-1T","org":"inclusionAI","family":"ling","series":"Ring-2.5","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2026-02-10","updated":"2026-09-24","gated":false,"params":{"total":1012.231,"active":null,"src":"safetensors","q":null,"stTotal":1012.231},"moe":true,"ctx":131072,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.75,"32768":3.02,"131072":12.08},"mem":{"bf16":{"w":2024.46,"t":2228.2},"fp8":{"w":1075.5,"t":1184.3},"q4":{"w":613.67,"t":676.3}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":1015.47,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ring-2.5-1T","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ring-2.5-1T","u":"https://huggingface.co/inclusionAI/Ring-2.5-1T"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ring-2.5-1T/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ring-2-5-1t/"},{"id":"ring-2-6-1t","name":"Ring-2.6-1T","hf":"inclusionAI/Ring-2.6-1T","org":"inclusionAI","family":"ling","series":"Ring-2.6","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2026-05-14","updated":"2026-09-24","gated":false,"params":{"total":1025.414,"active":null,"src":"safetensors","q":null,"stTotal":1025.414},"moe":true,"ctx":131072,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.75,"32768":3.02,"131072":12.08},"mem":{"bf16":{"w":2050.83,"t":2257.2},"fp8":{"w":1089.5,"t":1199.7},"q4":{"w":621.66,"t":685.1}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":1041.84,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ring-2.6-1T","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ring-2.6-1T","u":"https://huggingface.co/inclusionAI/Ring-2.6-1T"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ring-2.6-1T/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ring-2-6-1t/"},{"id":"ring-flash-2-0","name":"Ring-flash-2.0","hf":"inclusionAI/Ring-flash-2.0","org":"inclusionAI","family":"ling","series":"Ring-flash-2.0","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-09-19","updated":"2026-09-24","gated":false,"params":{"total":100,"active":6.1,"src":"card","q":"a total of 100B parameters, with only 6.1B activated per inference","stTotal":102.89},"moe":true,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54,"32768":2.15},"mem":{"bf16":{"w":200,"t":221},"fp8":{"w":106.25,"t":117.9},"q4":{"w":60.62,"t":67.7}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"h100","mac":"mac128"}},"disk":205.78,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ring-flash-2.0","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ring-flash-2.0","u":"https://huggingface.co/inclusionAI/Ring-flash-2.0"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ring-flash-2.0/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ring-flash-2-0/"},{"id":"ring-flash-linear-2-0","name":"Ring-flash-linear-2.0","hf":"inclusionAI/Ring-flash-linear-2.0","org":"inclusionAI","family":"ling","series":"Ring-flash-linear-2.0","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-09-25","updated":"2025-10-23","gated":false,"params":{"total":104.182,"active":6.1,"src":"safetensors","q":"while activating only 6.1B parameters","stTotal":104.182},"moe":true,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54,"32768":2.15,"131072":8.59},"mem":{"bf16":{"w":208.36,"t":230.2},"fp8":{"w":110.69,"t":122.8},"q4":{"w":63.16,"t":70.5}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"h100","mac":"mac128"}},"disk":208.37,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ring-flash-linear-2.0","kind":"main"}],"sources":[{"t":"Hugging Face · inclusionAI/Ring-flash-linear-2.0","u":"https://huggingface.co/inclusionAI/Ring-flash-linear-2.0"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ring-flash-linear-2.0/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/ring-flash-linear-2-0/"},{"id":"ring-mini-linear-2-0","name":"Ring-mini-linear-2.0","hf":"inclusionAI/Ring-mini-linear-2.0","org":"inclusionAI","family":"ling","series":"Ring-mini-linear-2.0","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-09-24","updated":"2025-10-23","gated":false,"params":{"total":16.4,"active":1.6,"src":"card","q":"while activating only 1.6B of its 16.4B total parameters","stTotal":16.423},"moe":true,"ctx":131072,"arch":{"L":20,"attn":20,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.34,"32768":1.34,"131072":5.37},"mem":{"bf16":{"w":32.8,"t":36.9},"fp8":{"w":17.42,"t":20},"q4":{"w":9.94,"t":11.8}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":32.85,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"inclusionAI/Ring-mini-linear-2.0","kind":"main"},{"id":"inclusionAI/Ring-mini-linear-2.0-GPTQ-int4","kind":"GPTQ/INT4"},{"id":"inclusionAI/Ring-flash-linear-2.0-GPTQ-int4","kind":"GPTQ/INT4"}],"sources":[{"t":"Hugging Face · inclusionAI/Ring-mini-linear-2.0","u":"https://huggingface.co/inclusionAI/Ring-mini-linear-2.0"},{"t":"config.json","u":"https://huggingface.co/inclusionAI/Ring-mini-linear-2.0/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ling/#m-ring-mini-linear-2-0"},{"id":"llama-3-1-8b-instruct","name":"Llama-3.1-8B-Instruct","hf":"meta-llama/Llama-3.1-8B-Instruct","org":"meta-llama","family":"llama","series":"Llama-3.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-07-18","updated":"2024-09-25","gated":true,"params":{"total":8.03,"active":null,"src":"safetensors","q":null,"stTotal":8.03},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":16.06,"t":19.2},"fp8":{"w":8.53,"t":11},"q4":{"w":4.87,"t":6.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.06,"native":"BF16","license":{"id":"llama3.1","name":"Llama 3.1 Community","link":"https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"llama3.1:8b","url":"https://ollama.com/library/llama3.1"}],"variants":[{"id":"meta-llama/Llama-3.1-8B-Instruct","kind":"Instruct"},{"id":"meta-llama/Llama-3.1-8B","kind":"main"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-3.1-8B-Instruct","u":"https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · llama3.1","u":"https://ollama.com/library/llama3.1"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-3-1-8b-instruct"},{"id":"llama-3-1-70b-instruct","name":"Llama-3.1-70B-Instruct","hf":"meta-llama/Llama-3.1-70B-Instruct","org":"meta-llama","family":"llama","series":"Llama-3.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-07-16","updated":"2024-12-15","gated":true,"params":{"total":70.554,"active":null,"src":"safetensors","q":null,"stTotal":70.554},"moe":false,"ctx":131072,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74,"131072":42.95},"mem":{"bf16":{"w":141.11,"t":158.4},"fp8":{"w":74.96,"t":85.6},"q4":{"w":42.77,"t":50.2}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"pro6000","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":141.11,"native":"BF16","license":{"id":"llama3.1","name":"Llama 3.1 Community","link":"https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"llama3.1:70b","url":"https://ollama.com/library/llama3.1"}],"variants":[{"id":"meta-llama/Llama-3.1-70B-Instruct","kind":"Instruct"},{"id":"meta-llama/Llama-3.1-70B","kind":"main"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-3.1-70B-Instruct","u":"https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · llama3.1","u":"https://ollama.com/library/llama3.1"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-3-1-70b-instruct"},{"id":"llama-3-1-405b","name":"Llama-3.1-405B","hf":"meta-llama/Llama-3.1-405B","org":"meta-llama","family":"llama","series":"Llama-3.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-07-16","updated":"2024-09-25","gated":true,"params":{"total":405.853,"active":null,"src":"safetensors","q":null,"stTotal":405.853},"moe":false,"ctx":131072,"arch":{"L":126,"attn":126,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":4.23,"32768":16.91,"131072":67.65},"mem":{"bf16":{"w":811.71,"t":897.6},"fp8":{"w":431.22,"t":479.1},"q4":{"w":246.05,"t":275.4}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":811.71,"native":"BF16","license":{"id":"llama3.1","name":"Llama 3.1 Community","link":"https://huggingface.co/meta-llama/Llama-3.1-405B/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"llama3.1:405b","url":"https://ollama.com/library/llama3.1"}],"variants":[{"id":"meta-llama/Llama-3.1-405B-FP8","kind":"FP8"},{"id":"meta-llama/Llama-3.1-405B","kind":"main"},{"id":"meta-llama/Llama-3.1-405B-Instruct","kind":"Instruct"},{"id":"meta-llama/Llama-3.1-405B-Instruct-FP8","kind":"Instruct/FP8"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-3.1-405B","u":"https://huggingface.co/meta-llama/Llama-3.1-405B"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-3.1-405B/blob/main/LICENSE"},{"t":"Ollama library · llama3.1","u":"https://ollama.com/library/llama3.1"}],"page":"https://aimap.page/en/models/compute/open-models/llama-3-1-405b/"},{"id":"llama-3-2-1b-instruct","name":"Llama-3.2-1B-Instruct","hf":"meta-llama/Llama-3.2-1B-Instruct","org":"meta-llama","family":"llama","series":"Llama-3.2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-18","updated":"2024-10-24","gated":true,"params":{"total":1.236,"active":null,"src":"safetensors","q":null,"stTotal":1.236},"moe":false,"ctx":131072,"arch":{"L":16,"attn":16,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.27,"32768":1.07,"131072":4.29},"mem":{"bf16":{"w":2.47,"t":3.5},"fp8":{"w":1.31,"t":2.2},"q4":{"w":0.75,"t":1.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.47,"native":"BF16","license":{"id":"llama3.2","name":"Llama 3.2 Community","link":"https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/blob/main/LICENSE.txt","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"llama3.2:1b","url":"https://ollama.com/library/llama3.2"}],"variants":[{"id":"meta-llama/Llama-3.2-1B-Instruct","kind":"Instruct"},{"id":"meta-llama/Llama-3.2-1B","kind":"main"},{"id":"meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8","kind":"Instruct/INT4"},{"id":"meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8","kind":"Instruct/INT4"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-3.2-1B-Instruct","u":"https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/blob/main/LICENSE.txt"},{"t":"Ollama library · llama3.2","u":"https://ollama.com/library/llama3.2"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-3-2-1b-instruct"},{"id":"llama-3-2-3b-instruct","name":"Llama-3.2-3B-Instruct","hf":"meta-llama/Llama-3.2-3B-Instruct","org":"meta-llama","family":"llama","series":"Llama-3.2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-18","updated":"2024-10-24","gated":true,"params":{"total":3.213,"active":null,"src":"safetensors","q":null,"stTotal":3.213},"moe":false,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.94,"32768":3.76,"131072":15.03},"mem":{"bf16":{"w":6.43,"t":8.5},"fp8":{"w":3.41,"t":5.2},"q4":{"w":1.95,"t":3.6}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.43,"native":"BF16","license":{"id":"llama3.2","name":"Llama 3.2 Community","link":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE.txt","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"llama3.2:3b","url":"https://ollama.com/library/llama3.2"}],"variants":[{"id":"meta-llama/Llama-3.2-3B-Instruct","kind":"Instruct"},{"id":"meta-llama/Llama-3.2-3B","kind":"main"},{"id":"meta-llama/Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8","kind":"Instruct/INT4"},{"id":"meta-llama/Llama-3.2-3B-Instruct-QLORA_INT4_EO8","kind":"Instruct/INT4"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-3.2-3B-Instruct","u":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE.txt"},{"t":"Ollama library · llama3.2","u":"https://ollama.com/library/llama3.2"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-3-2-3b-instruct"},{"id":"llama-3-2-11b-vision-instruct","name":"Llama-3.2-11B-Vision-Instruct","hf":"meta-llama/Llama-3.2-11B-Vision-Instruct","org":"meta-llama","family":"llama","series":"Llama-3.2-Vision","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-09-18","updated":"2024-12-04","gated":true,"params":{"total":10.67,"active":null,"src":"safetensors","q":null,"stTotal":10.67},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":21.34,"t":24},"fp8":{"w":11.34,"t":13},"q4":{"w":6.47,"t":7.6}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":21.34,"native":"BF16","license":{"id":"llama3.2","name":"Llama 3.2 Community","link":"https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct/blob/main/LICENSE.txt","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"meta-llama/Llama-3.2-11B-Vision-Instruct","kind":"Instruct"},{"id":"meta-llama/Llama-3.2-11B-Vision","kind":"main"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-3.2-11B-Vision-Instruct","u":"https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-3-2-11b-vision-instruct"},{"id":"llama-3-3-70b-instruct","name":"Llama-3.3-70B-Instruct","hf":"meta-llama/Llama-3.3-70B-Instruct","org":"meta-llama","family":"llama","series":"Llama-3.3","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-11-26","updated":"2024-12-21","gated":true,"params":{"total":70.554,"active":null,"src":"safetensors","q":null,"stTotal":70.554},"moe":false,"ctx":131072,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74,"131072":42.95},"mem":{"bf16":{"w":141.11,"t":158.4},"fp8":{"w":74.96,"t":85.6},"q4":{"w":42.77,"t":50.2}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"pro6000","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":141.11,"native":"BF16","license":{"id":"llama3.3","name":"Llama 3.3 Community","link":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"llama3.3:70b","url":"https://ollama.com/library/llama3.3"}],"variants":[{"id":"meta-llama/Llama-3.3-70B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-3.3-70B-Instruct","u":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · llama3.3","u":"https://ollama.com/library/llama3.3"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-3-3-70b-instruct"},{"id":"llama-4-maverick-17b-128e-instruct","name":"Llama-4-Maverick-17B-128E-Instruct","hf":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","org":"meta-llama","family":"llama","series":"Llama-4-Maverick","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-04-01","updated":"2025-05-22","gated":true,"params":{"total":401.584,"active":null,"src":"safetensors","q":null,"stTotal":401.584},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":803.17,"t":884},"fp8":{"w":426.68,"t":469.9},"q4":{"w":243.46,"t":268.3}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":803.17,"native":"BF16","license":{"id":"llama4","name":"Llama 4 Community","link":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","kind":"Instruct/FP8"},{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","kind":"Instruct"},{"id":"meta-llama/Llama-4-Maverick-17B-128E","kind":"main"},{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8-Original","kind":"Instruct/FP8"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-4-Maverick-17B-128E-Instruct","u":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/llama-4-maverick-17b-128e-instruct/"},{"id":"llama-4-scout-17b-16e-instruct","name":"Llama-4-Scout-17B-16E-Instruct","hf":"meta-llama/Llama-4-Scout-17B-16E-Instruct","org":"meta-llama","family":"llama","series":"Llama-4-Scout","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-04-02","updated":"2025-05-22","gated":true,"params":{"total":108.642,"active":null,"src":"safetensors","q":null,"stTotal":108.642},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":217.28,"t":239.5},"fp8":{"w":115.43,"t":127.5},"q4":{"w":65.86,"t":73}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":217.28,"native":"BF16","license":{"id":"llama4","name":"Llama 4 Community","link":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","kind":"Instruct"},{"id":"meta-llama/Llama-4-Scout-17B-16E","kind":"main"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-4-Scout-17B-16E-Instruct","u":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/llama-4-scout-17b-16e-instruct/"},{"id":"llama-guard-3-1b","name":"Llama-Guard-3-1B","hf":"meta-llama/Llama-Guard-3-1B","org":"meta-llama","family":"llama","series":"Llama-Guard-3","task":"guard","pipeline":"text-generation","tags":[],"released":"2024-09-20","updated":"2024-09-26","gated":true,"params":{"total":1.498,"active":null,"src":"safetensors","q":null,"stTotal":1.498},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":3,"t":3.8},"fp8":{"w":1.59,"t":2.3},"q4":{"w":0.91,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3,"native":"BF16","license":{"id":"llama3.2","name":"Llama 3.2 Community","link":"https://huggingface.co/meta-llama/Llama-Guard-3-1B/blob/main/LICENSE.txt","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"llama-guard3:1b","url":"https://ollama.com/library/llama-guard3"}],"variants":[{"id":"meta-llama/Llama-Guard-3-1B","kind":"main"},{"id":"meta-llama/Llama-Guard-3-1B-INT4","kind":"INT4"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-Guard-3-1B","u":"https://huggingface.co/meta-llama/Llama-Guard-3-1B"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-Guard-3-1B/blob/main/LICENSE.txt"},{"t":"Ollama library · llama-guard3","u":"https://ollama.com/library/llama-guard3"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-guard-3-1b"},{"id":"llama-guard-3-8b","name":"Llama-Guard-3-8B","hf":"meta-llama/Llama-Guard-3-8B","org":"meta-llama","family":"llama","series":"Llama-Guard-3","task":"guard","pipeline":"text-generation","tags":[],"released":"2024-07-22","updated":"2024-10-11","gated":true,"params":{"total":8.03,"active":null,"src":"safetensors","q":null,"stTotal":8.03},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":16.06,"t":18.2},"fp8":{"w":8.53,"t":9.9},"q4":{"w":4.87,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.06,"native":"BF16","license":{"id":"llama3.1","name":"Llama 3.1 Community","link":"https://huggingface.co/meta-llama/Llama-Guard-3-8B/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"llama-guard3:8b","url":"https://ollama.com/library/llama-guard3"}],"variants":[{"id":"meta-llama/Llama-Guard-3-8B","kind":"main"},{"id":"meta-llama/Llama-Guard-3-8B-INT8","kind":"INT8"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-Guard-3-8B","u":"https://huggingface.co/meta-llama/Llama-Guard-3-8B"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-Guard-3-8B/blob/main/LICENSE"},{"t":"Ollama library · llama-guard3","u":"https://ollama.com/library/llama-guard3"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-guard-3-8b"},{"id":"llama-guard-3-11b-vision","name":"Llama-Guard-3-11B-Vision","hf":"meta-llama/Llama-Guard-3-11B-Vision","org":"meta-llama","family":"llama","series":"Llama-Guard-3-Vision","task":"guard","pipeline":"image-text-to-text","tags":[],"released":"2024-09-20","updated":"2024-11-18","gated":true,"params":{"total":10.67,"active":null,"src":"safetensors","q":null,"stTotal":10.67},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":21.34,"t":24},"fp8":{"w":11.34,"t":13},"q4":{"w":6.47,"t":7.6}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":21.34,"native":"BF16","license":{"id":"llama3.2","name":"Llama 3.2 Community","link":"https://huggingface.co/meta-llama/Llama-Guard-3-11B-Vision/blob/main/LICENSE.txt","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"meta-llama/Llama-Guard-3-11B-Vision","kind":"main"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-Guard-3-11B-Vision","u":"https://huggingface.co/meta-llama/Llama-Guard-3-11B-Vision"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-Guard-3-11B-Vision/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-guard-3-11b-vision"},{"id":"llama-guard-4-12b","name":"Llama-Guard-4-12B","hf":"meta-llama/Llama-Guard-4-12B","org":"meta-llama","family":"llama","series":"Llama-Guard-4","task":"guard","pipeline":"image-text-to-text","tags":[],"released":"2025-04-23","updated":"2025-04-29","gated":true,"params":{"total":12.001,"active":null,"src":"safetensors","q":null,"stTotal":12.001},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":24,"t":26.9},"fp8":{"w":12.75,"t":14.5},"q4":{"w":7.28,"t":8.5}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24,"native":"BF16","license":{"id":"llama4","name":"Llama 4 Community","link":"https://huggingface.co/meta-llama/Llama-Guard-4-12B/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"meta-llama/Llama-Guard-4-12B","kind":"main"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-Guard-4-12B","u":"https://huggingface.co/meta-llama/Llama-Guard-4-12B"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-Guard-4-12B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-guard-4-12b"},{"id":"llama-prompt-guard-2-22m","name":"Llama-Prompt-Guard-2-22M","hf":"meta-llama/Llama-Prompt-Guard-2-22M","org":"meta-llama","family":"llama","series":"Llama-Prompt-Guard-2","task":"guard","pipeline":"text-classification","tags":[],"released":"2025-04-28","updated":"2025-04-29","gated":true,"params":{"total":0.071,"active":null,"src":"safetensors","q":null,"stTotal":0.071},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.14,"t":0.7},"fp8":{"w":0.08,"t":0.6},"q4":{"w":0.04,"t":0.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.28,"native":"F32","license":{"id":"llama4","name":"Llama 4 Community","link":"https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-22M/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"meta-llama/Llama-Prompt-Guard-2-22M","kind":"main"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-Prompt-Guard-2-22M","u":"https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-22M"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-22M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-prompt-guard-2-22m"},{"id":"llama-prompt-guard-2-86m","name":"Llama-Prompt-Guard-2-86M","hf":"meta-llama/Llama-Prompt-Guard-2-86M","org":"meta-llama","family":"llama","series":"Llama-Prompt-Guard-2","task":"guard","pipeline":"text-classification","tags":[],"released":"2025-04-28","updated":"2025-04-29","gated":true,"params":{"total":0.279,"active":null,"src":"safetensors","q":null,"stTotal":0.279},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.56,"t":1.1},"fp8":{"w":0.3,"t":0.8},"q4":{"w":0.17,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.12,"native":"F32","license":{"id":"llama4","name":"Llama 4 Community","link":"https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-86M/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"meta-llama/Llama-Prompt-Guard-2-86M","kind":"main"}],"sources":[{"t":"Hugging Face · meta-llama/Llama-Prompt-Guard-2-86M","u":"https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-86M"},{"t":"License","u":"https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-86M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-llama-prompt-guard-2-86m"},{"id":"prompt-guard-86m","name":"Prompt-Guard-86M","hf":"meta-llama/Prompt-Guard-86M","org":"meta-llama","family":"llama","series":"Prompt-Guard","task":"guard","pipeline":"text-classification","tags":[],"released":"2024-07-21","updated":"2025-11-12","gated":true,"params":{"total":0.279,"active":null,"src":"safetensors","q":null,"stTotal":0.279},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.56,"t":1.1},"fp8":{"w":0.3,"t":0.8},"q4":{"w":0.17,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.12,"native":"F32","license":{"id":"llama3.1","name":"Llama 3.1 Community","link":"https://huggingface.co/meta-llama/Prompt-Guard-86M/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"meta-llama/Prompt-Guard-86M","kind":"main"}],"sources":[{"t":"Hugging Face · meta-llama/Prompt-Guard-86M","u":"https://huggingface.co/meta-llama/Prompt-Guard-86M"},{"t":"License","u":"https://huggingface.co/meta-llama/Prompt-Guard-86M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/llama/#m-prompt-guard-86m"},{"id":"longcat-2-0","name":"LongCat-2.0","hf":"meituan-longcat/LongCat-2.0","org":"meituan-longcat","family":"longcat","series":"LongCat-2.0","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-07-05","updated":"2026-07-08","gated":false,"params":{"total":1600,"active":48,"src":"card","q":"1.6 trillion total parameters and ~48 billion activated per token","stTotal":1775.56},"moe":true,"ctx":262144,"arch":{"L":38,"attn":38,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.36,"32768":1.43,"131072":5.74},"mem":{"bf16":{"w":3200,"t":3520.9},"fp8":{"w":1700,"t":1870.9},"q4":{"w":970,"t":1067.9}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb300","mac":null},"q4":{"gpu":"8xb200","mac":null}},"disk":3551.71,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-2.0/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-2.0","kind":"main"},{"id":"meituan-longcat/LongCat-2.0-FP8","kind":"FP8"},{"id":"meituan-longcat/LongCat-2.0-INT8","kind":"INT8"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-2.0","u":"https://huggingface.co/meituan-longcat/LongCat-2.0"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-2.0/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-2.0/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/longcat-2-0/"},{"id":"longcat-audiodit-1b","name":"LongCat-AudioDiT-1B","hf":"meituan-longcat/LongCat-AudioDiT-1B","org":"meituan-longcat","family":"longcat","series":"LongCat-AudioDiT","task":"tts","pipeline":null,"tags":[],"released":"2026-03-30","updated":"2026-04-03","gated":false,"params":{"total":1.42,"active":null,"src":"safetensors","q":null,"stTotal":1.42},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":2.84,"t":3.6},"fp8":{"w":1.51,"t":2.2},"q4":{"w":0.86,"t":1.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.68,"native":"F32","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-AudioDiT-1B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-AudioDiT-1B","kind":"main"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-AudioDiT-1B","u":"https://huggingface.co/meituan-longcat/LongCat-AudioDiT-1B"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-AudioDiT-1B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-AudioDiT-1B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/longcat/#m-longcat-audiodit-1b"},{"id":"longcat-audiodit-3-5b","name":"LongCat-AudioDiT-3.5B","hf":"meituan-longcat/LongCat-AudioDiT-3.5B","org":"meituan-longcat","family":"longcat","series":"LongCat-AudioDiT","task":"tts","pipeline":null,"tags":[],"released":"2026-03-30","updated":"2026-04-03","gated":false,"params":{"total":3.834,"active":null,"src":"safetensors","q":null,"stTotal":3.834},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":7.67,"t":8.9},"fp8":{"w":4.07,"t":5},"q4":{"w":2.32,"t":3.1}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.34,"native":"F32","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-AudioDiT-3.5B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-AudioDiT-3.5B","kind":"main"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-AudioDiT-3.5B","u":"https://huggingface.co/meituan-longcat/LongCat-AudioDiT-3.5B"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-AudioDiT-3.5B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-AudioDiT-3.5B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/longcat/#m-longcat-audiodit-3-5b"},{"id":"longcat-flash-chat","name":"LongCat-Flash-Chat","hf":"meituan-longcat/LongCat-Flash-Chat","org":"meituan-longcat","family":"longcat","series":"LongCat-Flash","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-08-29","updated":"2025-09-24","gated":false,"params":{"total":560,"active":27,"src":"card","q":"560 billion total parameters … # Activated Params 27B","stTotal":561.863},"moe":true,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.26,"32768":1.06,"131072":4.23},"mem":{"bf16":{"w":1120,"t":1232.8},"fp8":{"w":595,"t":655.3},"q4":{"w":339.5,"t":374.2}},"fits":{"bf16":{"gpu":"8xb200","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1124,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-Flash-Chat/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Flash-Chat","kind":"Instruct"},{"id":"meituan-longcat/LongCat-Flash-Chat-FP8","kind":"Instruct/FP8"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Flash-Chat","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Chat"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Chat/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Chat/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/longcat-flash-chat/"},{"id":"longcat-flash-lite","name":"LongCat-Flash-Lite","hf":"meituan-longcat/LongCat-Flash-Lite","org":"meituan-longcat","family":"longcat","series":"LongCat-Flash-Lite","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-01-27","updated":"2026-02-06","gated":false,"params":{"total":68.5,"active":3,"src":"card","q":"68.5B parameter MoE model with approximately 3B activated parameters","stTotal":69.073},"moe":true,"ctx":327680,"arch":{"L":14,"attn":14,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.13,"32768":0.53,"131072":2.11},"mem":{"bf16":{"w":137,"t":151.3},"fp8":{"w":72.78,"t":80.7},"q4":{"w":41.53,"t":46.3}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"pro6000","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":138.18,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-Flash-Lite/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Flash-Lite-FP8","kind":"FP8"},{"id":"meituan-longcat/LongCat-Flash-Lite","kind":"main"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Flash-Lite","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Lite"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Lite/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Lite/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/longcat/#m-longcat-flash-lite"},{"id":"longcat-flash-lite-sparse","name":"LongCat-Flash-Lite-Sparse","hf":"meituan-longcat/LongCat-Flash-Lite-Sparse","org":"meituan-longcat","family":"longcat","series":"LongCat-Flash-Lite-Sparse","task":"llm","pipeline":"text-generation","tags":["ocr"],"released":"2026-07-31","updated":"2026-08-04","gated":false,"params":{"total":69,"active":3,"src":"card","q":"69B total parameters and approximately 3B activated parameters per token","stTotal":69.127},"moe":true,"ctx":983040,"arch":{"L":14,"attn":14,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.13,"32768":0.53,"131072":2.11},"mem":{"bf16":{"w":138,"t":152.4},"fp8":{"w":73.31,"t":81.3},"q4":{"w":41.83,"t":46.6}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"pro6000","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":138.29,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-Flash-Lite-Sparse/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Flash-Lite-Sparse","kind":"main"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Flash-Lite-Sparse","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Lite-Sparse"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Lite-Sparse/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Lite-Sparse/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/longcat/#m-longcat-flash-lite-sparse"},{"id":"longcat-flash-omni","name":"LongCat-Flash-Omni","hf":"meituan-longcat/LongCat-Flash-Omni","org":"meituan-longcat","family":"longcat","series":"LongCat-Flash-Omni","task":"omni","pipeline":"any-to-any","tags":[],"released":"2025-10-23","updated":"2025-11-11","gated":false,"params":{"total":560,"active":27,"src":"card","q":"560 billion parameters (with 27B activated)","stTotal":560.665},"moe":true,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.26,"32768":1.06,"131072":4.23},"mem":{"bf16":{"w":1120,"t":1232.8},"fp8":{"w":595,"t":655.3},"q4":{"w":339.5,"t":374.2}},"fits":{"bf16":{"gpu":"8xb200","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1121.6,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-Flash-Omni/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Flash-Omni","kind":"main"},{"id":"meituan-longcat/LongCat-Flash-Omni-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Flash-Omni","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Omni"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Omni/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Omni/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/longcat-flash-omni/"},{"id":"longcat-flash-thinking","name":"LongCat-Flash-Thinking","hf":"meituan-longcat/LongCat-Flash-Thinking","org":"meituan-longcat","family":"longcat","series":"LongCat-Flash-Thinking","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-09-21","updated":"2025-09-24","gated":false,"params":{"total":560,"active":27,"src":"card","q":"560 billion total parameters … # Activated Params 27B","stTotal":561.863},"moe":true,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.26,"32768":1.06,"131072":4.23},"mem":{"bf16":{"w":1120,"t":1232.8},"fp8":{"w":595,"t":655.3},"q4":{"w":339.5,"t":374.2}},"fits":{"bf16":{"gpu":"8xb200","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1124,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Flash-Thinking","kind":"main"},{"id":"meituan-longcat/LongCat-Flash-Thinking-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Flash-Thinking","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/longcat-flash-thinking/"},{"id":"longcat-flash-thinking-2601","name":"LongCat-Flash-Thinking-2601","hf":"meituan-longcat/LongCat-Flash-Thinking-2601","org":"meituan-longcat","family":"longcat","series":"LongCat-Flash-Thinking","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2026-01-14","updated":"2026-01-23","gated":false,"params":{"total":560,"active":27,"src":"card","q":"560 billion total parameters … # Activated Params 27B","stTotal":561.863},"moe":true,"ctx":983040,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.26,"32768":1.06,"131072":4.23},"mem":{"bf16":{"w":1120,"t":1232.8},"fp8":{"w":595,"t":655.3},"q4":{"w":339.5,"t":374.2}},"fits":{"bf16":{"gpu":"8xb200","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1124,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Flash-Thinking-2601","kind":"main"},{"id":"meituan-longcat/LongCat-Flash-Thinking-2601-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Flash-Thinking-2601","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/longcat-flash-thinking-2601/"},{"id":"longcat-flash-thinking-zigzag","name":"LongCat-Flash-Thinking-ZigZag","hf":"meituan-longcat/LongCat-Flash-Thinking-ZigZag","org":"meituan-longcat","family":"longcat","series":"LongCat-Flash-Thinking-ZigZag","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2026-01-23","updated":"2026-02-02","gated":false,"params":{"total":561.863,"active":null,"src":"safetensors","q":null,"stTotal":561.863},"moe":true,"ctx":983040,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.26,"32768":1.06,"131072":4.23},"mem":{"bf16":{"w":1123.73,"t":1236.9},"fp8":{"w":596.98,"t":657.4},"q4":{"w":340.63,"t":375.5}},"fits":{"bf16":{"gpu":"8xb200","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1124,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-ZigZag/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Flash-Thinking-ZigZag","kind":"main"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Flash-Thinking-ZigZag","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-ZigZag"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-ZigZag/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-ZigZag/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/longcat-flash-thinking-zigzag/"},{"id":"longcat-heavymode-summary","name":"LongCat-HeavyMode-Summary","hf":"meituan-longcat/LongCat-HeavyMode-Summary","org":"meituan-longcat","family":"longcat","series":"LongCat-HeavyMode-Summary","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-01-14","updated":"2026-01-14","gated":false,"params":{"total":561.863,"active":null,"src":"safetensors","q":null,"stTotal":561.863},"moe":true,"ctx":983040,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.26,"32768":1.06,"131072":4.23},"mem":{"bf16":{"w":1123.73,"t":1236.9},"fp8":{"w":596.98,"t":657.4},"q4":{"w":340.63,"t":375.5}},"fits":{"bf16":{"gpu":"8xb200","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1124,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-HeavyMode-Summary/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-HeavyMode-Summary","kind":"main"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-HeavyMode-Summary","u":"https://huggingface.co/meituan-longcat/LongCat-HeavyMode-Summary"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-HeavyMode-Summary/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-HeavyMode-Summary/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/longcat-heavymode-summary/"},{"id":"longcat-image","name":"LongCat-Image","hf":"meituan-longcat/LongCat-Image","org":"meituan-longcat","family":"longcat","series":"LongCat-Image","task":"image","pipeline":"text-to-image","tags":[],"released":"2025-12-04","updated":"2025-12-16","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":29.29,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Image","kind":"main"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Image","u":"https://huggingface.co/meituan-longcat/LongCat-Image"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Image/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/longcat/#m-longcat-image"},{"id":"longcat-image-dev","name":"LongCat-Image-Dev","hf":"meituan-longcat/LongCat-Image-Dev","org":"meituan-longcat","family":"longcat","series":"LongCat-Image-Dev","task":"image","pipeline":"text-to-image","tags":[],"released":"2025-12-04","updated":"2025-12-16","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":29.29,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Image-Dev","kind":"main"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Image-Dev","u":"https://huggingface.co/meituan-longcat/LongCat-Image-Dev"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Image-Dev/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/longcat/#m-longcat-image-dev"},{"id":"longcat-image-edit","name":"LongCat-Image-Edit","hf":"meituan-longcat/LongCat-Image-Edit","org":"meituan-longcat","family":"longcat","series":"LongCat-Image-Edit","task":"image","pipeline":"image-to-image","tags":[],"released":"2025-12-05","updated":"2025-12-16","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":29.29,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Image-Edit","kind":"main"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Image-Edit","u":"https://huggingface.co/meituan-longcat/LongCat-Image-Edit"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Image-Edit/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/longcat/#m-longcat-image-edit"},{"id":"longcat-image-edit-turbo","name":"LongCat-Image-Edit-Turbo","hf":"meituan-longcat/LongCat-Image-Edit-Turbo","org":"meituan-longcat","family":"longcat","series":"LongCat-Image-Edit-Turbo","task":"image","pipeline":"image-to-image","tags":[],"released":"2026-02-03","updated":"2026-02-03","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":29.29,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Image-Edit-Turbo","kind":"main"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Image-Edit-Turbo","u":"https://huggingface.co/meituan-longcat/LongCat-Image-Edit-Turbo"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Image-Edit-Turbo/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/longcat/#m-longcat-image-edit-turbo"},{"id":"longcat-video","name":"LongCat-Video","hf":"meituan-longcat/LongCat-Video","org":"meituan-longcat","family":"longcat","series":"LongCat-Video","task":"video","pipeline":"text-to-video","tags":[],"released":"2025-10-24","updated":"2025-10-29","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":83.29,"native":null,"license":{"id":"mit","name":"MIT","link":"https://huggingface.co/meituan-longcat/LongCat-Video/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"meituan-longcat/LongCat-Video-Avatar-1.5","kind":"main"},{"id":"meituan-longcat/LongCat-Video","kind":"main"}],"sources":[{"t":"Hugging Face · meituan-longcat/LongCat-Video","u":"https://huggingface.co/meituan-longcat/LongCat-Video"},{"t":"config.json","u":"https://huggingface.co/meituan-longcat/LongCat-Video/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/meituan-longcat/LongCat-Video/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/longcat/#m-longcat-video"},{"id":"ltx-2","name":"LTX-2","hf":"Lightricks/LTX-2","org":"Lightricks","family":"ltx","series":"LTX-2","task":"video","pipeline":"image-to-video","tags":[],"released":"2026-01-03","updated":"2026-10-22","gated":false,"params":{"total":18.876,"active":null,"src":"safetensors","q":null,"stTotal":18.876},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":37.75,"t":42},"fp8":{"w":20.06,"t":22.6},"q4":{"w":11.44,"t":13.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":169.65,"native":"BF16","license":{"id":"ltx-2-community-license-agreement","name":"ltx-2-community-license-agreement","link":"https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2","cls":"custom"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Lightricks/LTX-2","kind":"main"}],"sources":[{"t":"Hugging Face · Lightricks/LTX-2","u":"https://huggingface.co/Lightricks/LTX-2"},{"t":"License","u":"https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2"}],"page":"https://aimap.page/en/models/compute/open-models/family/ltx/#m-ltx-2"},{"id":"ltx-2-3","name":"LTX-2.3","hf":"Lightricks/LTX-2.3","org":"Lightricks","family":"ltx","series":"LTX-2.3","task":"video","pipeline":"image-to-video","tags":[],"released":"2026-03-04","updated":"2026-10-22","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":156.01,"native":null,"license":{"id":"ltx-2-community-license-agreement","name":"ltx-2-community-license-agreement","link":"https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2","cls":"custom"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Lightricks/LTX-2.3","kind":"main"},{"id":"Lightricks/LTX-2.3-fp8","kind":"FP8"},{"id":"Lightricks/LTX-2.3-nvfp4","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · Lightricks/LTX-2.3","u":"https://huggingface.co/Lightricks/LTX-2.3"},{"t":"License","u":"https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2"}],"page":"https://aimap.page/en/models/compute/open-models/family/ltx/#m-ltx-2-3"},{"id":"ltx-2-5","name":"LTX-2.5","hf":"Lightricks/LTX-2.5","org":"Lightricks","family":"ltx","series":"LTX-2.5","task":"video","pipeline":"image-to-video","tags":[],"released":"2026-07-23","updated":"2026-10-11","gated":true,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":200.85,"native":null,"license":{"id":"ltx-2.x-community-license-agreement","name":"ltx-2.x-community-license-agreement","link":"https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2_x","cls":"custom"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Lightricks/LTX-2.5","kind":"main"},{"id":"Lightricks/LTX-2.5-Diffusers","kind":"Diffusers"}],"sources":[{"t":"Hugging Face · Lightricks/LTX-2.5","u":"https://huggingface.co/Lightricks/LTX-2.5"},{"t":"License","u":"https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2_x"}],"page":"https://aimap.page/en/models/compute/open-models/family/ltx/#m-ltx-2-5"},{"id":"ltx-video","name":"LTX-Video","hf":"Lightricks/LTX-Video","org":"Lightricks","family":"ltx","series":"LTX-Video","task":"video","pipeline":"image-to-video","tags":[],"released":"2024-10-31","updated":"2025-07-16","gated":false,"params":{"total":1.923,"active":null,"src":"safetensors","q":null,"stTotal":1.923},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":3.85,"t":4.7},"fp8":{"w":2.04,"t":2.7},"q4":{"w":1.17,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":225.39,"native":"F32","license":{"id":"other","name":"other","link":"https://huggingface.co/Lightricks/LTX-Video/blob/main/LTX-Video-Open-Weights-License-0.X.txt","cls":"custom"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Lightricks/LTX-Video","kind":"main"}],"sources":[{"t":"Hugging Face · Lightricks/LTX-Video","u":"https://huggingface.co/Lightricks/LTX-Video"},{"t":"License","u":"https://huggingface.co/Lightricks/LTX-Video/blob/main/LTX-Video-Open-Weights-License-0.X.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/ltx/#m-ltx-video"},{"id":"ltx-video-0-9-5","name":"LTX-Video-0.9.5","hf":"Lightricks/LTX-Video-0.9.5","org":"Lightricks","family":"ltx","series":"LTX-Video-0.9.5","task":"video","pipeline":"text-to-video","tags":[],"released":"2025-03-16","updated":"2025-05-06","gated":false,"params":{"total":1.923,"active":null,"src":"safetensors","q":null,"stTotal":1.923},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":3.85,"t":4.7},"fp8":{"w":2.04,"t":2.7},"q4":{"w":1.17,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":25.39,"native":"BF16","license":{"id":"other","name":"other","link":"https://huggingface.co/Lightricks/LTX-Video-0.9.5/blob/main/ltx-video-2b-v0.9.5.license.txt","cls":"custom"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Lightricks/LTX-Video-0.9.5","kind":"main"}],"sources":[{"t":"Hugging Face · Lightricks/LTX-Video-0.9.5","u":"https://huggingface.co/Lightricks/LTX-Video-0.9.5"},{"t":"License","u":"https://huggingface.co/Lightricks/LTX-Video-0.9.5/blob/main/ltx-video-2b-v0.9.5.license.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/ltx/#m-ltx-video-0-9-5"},{"id":"ltx-video-0-9-7-dev","name":"LTX-Video-0.9.7-dev","hf":"Lightricks/LTX-Video-0.9.7-dev","org":"Lightricks","family":"ltx","series":"LTX-Video-0.9.7-dev","task":"video","pipeline":"text-to-video","tags":[],"released":"2025-05-13","updated":"2025-07-08","gated":false,"params":{"total":13.043,"active":null,"src":"safetensors","q":null,"stTotal":13.043},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":26.09,"t":29.2},"fp8":{"w":13.86,"t":15.7},"q4":{"w":7.91,"t":9.2}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":47.63,"native":"BF16","license":{"id":"other","name":"other","link":"https://huggingface.co/Lightricks/LTX-Video-0.9.7-dev/blob/main/LTX-Video-Open-Weights-License-0.X.txt","cls":"custom"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Lightricks/LTX-Video-0.9.7-dev","kind":"main"}],"sources":[{"t":"Hugging Face · Lightricks/LTX-Video-0.9.7-dev","u":"https://huggingface.co/Lightricks/LTX-Video-0.9.7-dev"},{"t":"License","u":"https://huggingface.co/Lightricks/LTX-Video-0.9.7-dev/blob/main/LTX-Video-Open-Weights-License-0.X.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/ltx/#m-ltx-video-0-9-7-dev"},{"id":"ltx-video-0-9-7-distilled","name":"LTX-Video-0.9.7-distilled","hf":"Lightricks/LTX-Video-0.9.7-distilled","org":"Lightricks","family":"ltx","series":"LTX-Video-0.9.7-distilled","task":"video","pipeline":"text-to-video","tags":[],"released":"2025-05-14","updated":"2025-07-08","gated":false,"params":{"total":13.043,"active":null,"src":"safetensors","q":null,"stTotal":13.043},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":26.09,"t":29.2},"fp8":{"w":13.86,"t":15.7},"q4":{"w":7.91,"t":9.2}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":47.63,"native":"BF16","license":{"id":"other","name":"other","link":"https://huggingface.co/Lightricks/LTX-Video-0.9.7-distilled/blob/main/LTX-Video-Open-Weights-License-0.X.txt","cls":"custom"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Lightricks/LTX-Video-0.9.7-distilled","kind":"main"}],"sources":[{"t":"Hugging Face · Lightricks/LTX-Video-0.9.7-distilled","u":"https://huggingface.co/Lightricks/LTX-Video-0.9.7-distilled"},{"t":"License","u":"https://huggingface.co/Lightricks/LTX-Video-0.9.7-distilled/blob/main/LTX-Video-Open-Weights-License-0.X.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/ltx/#m-ltx-video-0-9-7-distilled"},{"id":"ltx-video-0-9-8-13b-distilled","name":"LTX-Video-0.9.8-13B-distilled","hf":"Lightricks/LTX-Video-0.9.8-13B-distilled","org":"Lightricks","family":"ltx","series":"LTX-Video-0.9.8-distilled","task":"video","pipeline":"image-to-video","tags":[],"released":"2025-07-17","updated":"2025-07-17","gated":false,"params":{"total":13.043,"active":null,"src":"safetensors","q":null,"stTotal":13.043},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":26.09,"t":29.2},"fp8":{"w":13.86,"t":15.7},"q4":{"w":7.91,"t":9.2}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":92.76,"native":"BF16","license":{"id":"other","name":"other","link":"https://huggingface.co/Lightricks/LTX-Video-0.9.8-13B-distilled/blob/main/LTX-Video-Open-Weights-License-0.X.txt","cls":"custom"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Lightricks/LTX-Video-0.9.8-13B-distilled","kind":"main"}],"sources":[{"t":"Hugging Face · Lightricks/LTX-Video-0.9.8-13B-distilled","u":"https://huggingface.co/Lightricks/LTX-Video-0.9.8-13B-distilled"},{"t":"License","u":"https://huggingface.co/Lightricks/LTX-Video-0.9.8-13B-distilled/blob/main/LTX-Video-Open-Weights-License-0.X.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/ltx/#m-ltx-video-0-9-8-13b-distilled"},{"id":"mimo-7b-base","name":"MiMo-7B-Base","hf":"XiaomiMiMo/MiMo-7B-Base","org":"XiaomiMiMo","family":"mimo","series":"MiMo","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-29","updated":"2025-06-05","gated":false,"params":{"total":7.833,"active":null,"src":"safetensors","q":null,"stTotal":7.833},"moe":false,"ctx":32768,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":15.67,"t":18.9},"fp8":{"w":8.32,"t":10.9},"q4":{"w":4.75,"t":6.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.67,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-7B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-7B-Base","u":"https://huggingface.co/XiaomiMiMo/MiMo-7B-Base"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-7B-Base/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mimo/#m-mimo-7b-base"},{"id":"mimo-v2-5","name":"MiMo-V2.5","hf":"XiaomiMiMo/MiMo-V2.5","org":"XiaomiMiMo","family":"mimo","series":"MiMo","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-27","updated":"2026-07-09","gated":false,"params":{"total":310,"active":15,"src":"card","q":"310B total / 15B activated parameters","stTotal":310.756},"moe":true,"ctx":1048576,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1536,"kvMethod":"gqa","exotic":["swa_num_attention_heads"]},"kv":null,"mem":{"bf16":{"w":620,"t":682.5},"fp8":{"w":329.38,"t":362.8},"q4":{"w":187.94,"t":207.2}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":315.04,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-V2.5","kind":"main"},{"id":"XiaomiMiMo/MiMo-V2.5-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-V2.5","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/mimo-v2-5/"},{"id":"mimo-v2-5-asr","name":"MiMo-V2.5-ASR","hf":"XiaomiMiMo/MiMo-V2.5-ASR","org":"XiaomiMiMo","family":"mimo","series":"MiMo-ASR","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-04-23","updated":"2026-04-24","gated":false,"params":{"total":7.623,"active":null,"src":"safetensors","q":null,"stTotal":7.623},"moe":false,"ctx":8192,"arch":null,"kv":null,"mem":{"bf16":{"w":15.25,"t":17.3},"fp8":{"w":8.1,"t":9.4},"q4":{"w":4.62,"t":5.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":32.07,"native":"F32","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-V2.5-ASR","kind":"main"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-V2.5-ASR","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-ASR"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-ASR/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mimo/#m-mimo-v2-5-asr"},{"id":"mimo-audio-7b-instruct","name":"MiMo-Audio-7B-Instruct","hf":"XiaomiMiMo/MiMo-Audio-7B-Instruct","org":"XiaomiMiMo","family":"mimo","series":"MiMo-Audio","task":"omni","pipeline":"any-to-any","tags":[],"released":"2025-09-18","updated":"2026-06-17","gated":false,"params":{"total":8.019,"active":null,"src":"safetensors","q":null,"stTotal":8.019},"moe":false,"ctx":8192,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21},"mem":{"bf16":{"w":16.04,"t":19.4},"fp8":{"w":8.52,"t":11.1},"q4":{"w":4.86,"t":7.1}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.04,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"XiaomiMiMo/MiMo-Audio-7B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-Audio-7B-Instruct","u":"https://huggingface.co/XiaomiMiMo/MiMo-Audio-7B-Instruct"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-Audio-7B-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mimo/#m-mimo-audio-7b-instruct"},{"id":"mimo-v2-6-distill-qwen-9b","name":"MiMo-V2.6-Distill-Qwen-9B","hf":"XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B","org":"XiaomiMiMo","family":"mimo","series":"MiMo-Distill-Qwen","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-09-21","updated":"2026-09-22","gated":false,"params":{"total":9.41,"active":null,"src":"safetensors","q":null,"stTotal":9.41},"moe":false,"ctx":262144,"arch":{"L":32,"attn":8,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.27,"32768":1.07,"131072":4.29},"mem":{"bf16":{"w":18.82,"t":21.5},"fp8":{"w":10,"t":11.8},"q4":{"w":5.7,"t":7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":18.82,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B","kind":"main"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/mimo-v2-6-distill-qwen-9b/"},{"id":"mimo-v2-flash","name":"MiMo-V2-Flash","hf":"XiaomiMiMo/MiMo-V2-Flash","org":"XiaomiMiMo","family":"mimo","series":"MiMo-Flash","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-12-16","updated":"2026-07-09","gated":false,"params":{"total":309,"active":15,"src":"card","q":"309B total parameters and 15B active parameters","stTotal":309.767},"moe":true,"ctx":262144,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1536,"kvMethod":"gqa","exotic":["swa_num_attention_heads"]},"kv":null,"mem":{"bf16":{"w":618,"t":680.3},"fp8":{"w":328.31,"t":361.6},"q4":{"w":187.33,"t":206.6}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":313.06,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-V2-Flash","kind":"main"},{"id":"XiaomiMiMo/MiMo-V2-Flash-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-V2-Flash","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/mimo-v2-flash/"},{"id":"mimo-v2-6-flash-mopd","name":"MiMo-V2.6-Flash-MOPD","hf":"XiaomiMiMo/MiMo-V2.6-Flash-MOPD","org":"XiaomiMiMo","family":"mimo","series":"MiMo-Flash-MOPD","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-09-27","updated":"2026-10-09","gated":false,"params":{"total":309,"active":15,"src":"card","q":"309B total / 15B activated parameters","stTotal":310.756},"moe":true,"ctx":1048576,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1536,"kvMethod":"gqa","exotic":["swa_num_attention_heads"]},"kv":null,"mem":{"bf16":{"w":618,"t":680.3},"fp8":{"w":328.31,"t":361.6},"q4":{"w":187.33,"t":206.6}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":172.93,"native":"U8","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-V2.6-Flash-MOPD","kind":"main"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-V2.6-Flash-MOPD","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-MOPD"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-MOPD/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/mimo-v2-6-flash-mopd/"},{"id":"mimo-v2-6-flash-rl","name":"MiMo-V2.6-Flash-RL","hf":"XiaomiMiMo/MiMo-V2.6-Flash-RL","org":"XiaomiMiMo","family":"mimo","series":"MiMo-Flash-RL","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2026-09-21","updated":"2026-10-09","gated":false,"params":{"total":309,"active":15,"src":"card","q":"309B total / 15B activated parameters","stTotal":310.756},"moe":true,"ctx":1048576,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1536,"kvMethod":"gqa","exotic":["swa_num_attention_heads"]},"kv":null,"mem":{"bf16":{"w":618,"t":680.3},"fp8":{"w":328.31,"t":361.6},"q4":{"w":187.33,"t":206.6}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":172.93,"native":"U8","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-V2.6-Flash-RL","kind":"main"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-V2.6-Flash-RL","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/mimo-v2-6-flash-rl/"},{"id":"mimo-v2-5-pro","name":"MiMo-V2.5-Pro","hf":"XiaomiMiMo/MiMo-V2.5-Pro","org":"XiaomiMiMo","family":"mimo","series":"MiMo-Pro","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-27","updated":"2026-07-09","gated":false,"params":{"total":1020,"active":42,"src":"card","q":"1.02T total parameters and 42B active parameters","stTotal":1023.183},"moe":true,"ctx":1048576,"arch":{"L":70,"attn":70,"slide":0,"win":null,"kvElems":3072,"kvMethod":"gqa","exotic":["swa_num_attention_heads"]},"kv":null,"mem":{"bf16":{"w":2040,"t":2244.5},"fp8":{"w":1083.75,"t":1192.6},"q4":{"w":618.38,"t":680.7}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":1033.39,"native":"F8_E4M3","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-V2.5-Pro","kind":"main"},{"id":"XiaomiMiMo/MiMo-V2.5-Pro-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-V2.5-Pro","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/mimo-v2-5-pro/"},{"id":"mimo-v2-6-pro-mopd","name":"MiMo-V2.6-Pro-MOPD","hf":"XiaomiMiMo/MiMo-V2.6-Pro-MOPD","org":"XiaomiMiMo","family":"mimo","series":"MiMo-Pro-MOPD","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-09-27","updated":"2026-10-09","gated":false,"params":{"total":1020,"active":42,"src":"card","q":"1.02T total / 42B activated parameters","stTotal":1024.217},"moe":true,"ctx":1048576,"arch":{"L":70,"attn":70,"slide":0,"win":null,"kvElems":3072,"kvMethod":"gqa","exotic":["swa_num_attention_heads"]},"kv":null,"mem":{"bf16":{"w":2040,"t":2244.5},"fp8":{"w":1083.75,"t":1192.6},"q4":{"w":618.38,"t":680.7}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":566.05,"native":"U8","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-V2.6-Pro-MOPD","kind":"main"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-V2.6-Pro-MOPD","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-MOPD"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-MOPD/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/mimo-v2-6-pro-mopd/"},{"id":"mimo-v2-6-pro-rl","name":"MiMo-V2.6-Pro-RL","hf":"XiaomiMiMo/MiMo-V2.6-Pro-RL","org":"XiaomiMiMo","family":"mimo","series":"MiMo-Pro-RL","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2026-09-21","updated":"2026-10-09","gated":false,"params":{"total":1020,"active":42,"src":"card","q":"1.02T total / 42B activated parameters","stTotal":1024.217},"moe":true,"ctx":1048576,"arch":{"L":70,"attn":70,"slide":0,"win":null,"kvElems":3072,"kvMethod":"gqa","exotic":["swa_num_attention_heads"]},"kv":null,"mem":{"bf16":{"w":2040,"t":2244.5},"fp8":{"w":1083.75,"t":1192.6},"q4":{"w":618.38,"t":680.7}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":566.05,"native":"U8","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-V2.6-Pro-RL","kind":"main"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-V2.6-Pro-RL","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/mimo-v2-6-pro-rl/"},{"id":"mimo-7b-rl","name":"MiMo-7B-RL","hf":"XiaomiMiMo/MiMo-7B-RL","org":"XiaomiMiMo","family":"mimo","series":"MiMo-RL","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-04-29","updated":"2025-06-05","gated":false,"params":{"total":7.833,"active":null,"src":"safetensors","q":null,"stTotal":7.833},"moe":false,"ctx":32768,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":15.67,"t":18.9},"fp8":{"w":8.32,"t":10.9},"q4":{"w":4.75,"t":6.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.67,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-7B-RL","kind":"main"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-7B-RL","u":"https://huggingface.co/XiaomiMiMo/MiMo-7B-RL"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-7B-RL/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mimo/#m-mimo-7b-rl"},{"id":"mimo-vl-7b-rl-2508","name":"MiMo-VL-7B-RL-2508","hf":"XiaomiMiMo/MiMo-VL-7B-RL-2508","org":"XiaomiMiMo","family":"mimo","series":"MiMo-VL-RL","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-08-07","updated":"2025-08-21","gated":false,"params":{"total":8.306,"active":null,"src":"safetensors","q":null,"stTotal":8.306},"moe":false,"ctx":128000,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":16.61,"t":20},"fp8":{"w":8.83,"t":11.4},"q4":{"w":5.04,"t":7.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.61,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"XiaomiMiMo/MiMo-VL-7B-RL-2508","kind":"main"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-VL-7B-RL-2508","u":"https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL-2508"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL-2508/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mimo/#m-mimo-vl-7b-rl-2508"},{"id":"mimo-vl-7b-rl","name":"MiMo-VL-7B-RL","hf":"XiaomiMiMo/MiMo-VL-7B-RL","org":"XiaomiMiMo","family":"mimo","series":"MiMo-VL-RL","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-05-30","updated":"2025-06-07","gated":false,"params":{"total":8.306,"active":null,"src":"safetensors","q":null,"stTotal":8.306},"moe":false,"ctx":128000,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":16.61,"t":20},"fp8":{"w":8.83,"t":11.4},"q4":{"w":5.04,"t":7.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.61,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"XiaomiMiMo/MiMo-VL-7B-RL","kind":"main"},{"id":"XiaomiMiMo/MiMo-VL-7B-RL-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · XiaomiMiMo/MiMo-VL-7B-RL","u":"https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL"},{"t":"config.json","u":"https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mimo/#m-mimo-vl-7b-rl"},{"id":"minicpm-embedding","name":"MiniCPM-Embedding","hf":"openbmb/MiniCPM-Embedding","org":"openbmb","family":"minicpm","series":"MiniCPM-Embedding","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2024-09-04","updated":"2025-01-23","gated":false,"params":{"total":2.725,"active":null,"src":"safetensors","q":null,"stTotal":2.725},"moe":false,"ctx":512,"arch":null,"kv":null,"mem":{"bf16":{"w":5.45,"t":6.5},"fp8":{"w":2.9,"t":3.7},"q4":{"w":1.65,"t":2.3}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.45,"native":"BF16","license":{"id":null,"name":null,"link":null,"cls":"unknown"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM-Embedding","kind":"main"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-Embedding","u":"https://huggingface.co/openbmb/MiniCPM-Embedding"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-Embedding/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm-embedding"},{"id":"minicpm-embedding-light","name":"MiniCPM-Embedding-Light","hf":"openbmb/MiniCPM-Embedding-Light","org":"openbmb","family":"minicpm","series":"MiniCPM-Embedding-Light","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2025-01-17","updated":"2026-01-12","gated":false,"params":{"total":0.434,"active":null,"src":"safetensors","q":null,"stTotal":0.434},"moe":false,"ctx":4096,"arch":null,"kv":null,"mem":{"bf16":{"w":0.87,"t":1.5},"fp8":{"w":0.46,"t":1},"q4":{"w":0.26,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.87,"native":"BF16","license":{"id":null,"name":null,"link":null,"cls":"unknown"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM-Embedding-Light","kind":"main"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-Embedding-Light","u":"https://huggingface.co/openbmb/MiniCPM-Embedding-Light"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-Embedding-Light/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm-embedding-light"},{"id":"minicpm-llama3-v-2-5","name":"MiniCPM-Llama3-V-2_5","hf":"openbmb/MiniCPM-Llama3-V-2_5","org":"openbmb","family":"minicpm","series":"MiniCPM-Llama3-V-2_5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-05-19","updated":"2025-01-15","gated":false,"params":{"total":8.537,"active":null,"src":"safetensors","q":null,"stTotal":8.537},"moe":false,"ctx":8192,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07},"mem":{"bf16":{"w":17.07,"t":20.4},"fp8":{"w":9.07,"t":11.5},"q4":{"w":5.18,"t":7.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":17.07,"native":"F16","license":{"id":null,"name":null,"link":null,"cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM-Llama3-V-2_5","kind":"main"},{"id":"openbmb/MiniCPM-Llama3-V-2_5-gguf","kind":"GGUF"},{"id":"openbmb/MiniCPM-Llama3-V-2_5-int4","kind":"INT4"},{"id":"openbmb/MiniCPM-Llama3-V-2_5-GPTQ","kind":"GPTQ"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-Llama3-V-2_5","u":"https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm-llama3-v-2-5"},{"id":"minicpm-sala","name":"MiniCPM-SALA","hf":"openbmb/MiniCPM-SALA","org":"openbmb","family":"minicpm","series":"MiniCPM-SALA","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-02-11","updated":"2026-05-07","gated":false,"params":{"total":9.477,"active":null,"src":"safetensors","q":null,"stTotal":9.477},"moe":false,"ctx":524288,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.27,"32768":1.07,"131072":4.29},"mem":{"bf16":{"w":18.95,"t":21.6},"fp8":{"w":10.07,"t":11.8},"q4":{"w":5.75,"t":7.1}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":18.95,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM-SALA","kind":"main"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-SALA","u":"https://huggingface.co/openbmb/MiniCPM-SALA"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-SALA/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm-sala"},{"id":"minicpm-v-2-6","name":"MiniCPM-V-2_6","hf":"openbmb/MiniCPM-V-2_6","org":"openbmb","family":"minicpm","series":"MiniCPM-V-2_6","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-08-04","updated":"2025-06-13","gated":true,"params":{"total":8.099,"active":null,"src":"safetensors","q":null,"stTotal":8.099},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":16.2,"t":18.3},"fp8":{"w":8.61,"t":10},"q4":{"w":4.91,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.2,"native":"BF16","license":{"id":null,"name":null,"link":null,"cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM-V-2_6","kind":"main"},{"id":"openbmb/MiniCPM-V-2_6-gguf","kind":"GGUF"},{"id":"openbmb/MiniCPM-V-2_6-int4","kind":"INT4"},{"id":"openbmb/MiniCPM-V-2_6-GPTQ","kind":"GPTQ"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-V-2_6","u":"https://huggingface.co/openbmb/MiniCPM-V-2_6"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm-v-2-6"},{"id":"minicpm-v-4","name":"MiniCPM-V-4","hf":"openbmb/MiniCPM-V-4","org":"openbmb","family":"minicpm","series":"MiniCPM-V-4","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-07-12","updated":"2026-08-18","gated":false,"params":{"total":4.06,"active":null,"src":"safetensors","q":null,"stTotal":4.06},"moe":false,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.27,"32768":1.07},"mem":{"bf16":{"w":8.12,"t":9.7},"fp8":{"w":4.31,"t":5.5},"q4":{"w":2.46,"t":3.5}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.12,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM-V-4","kind":"main"},{"id":"openbmb/MiniCPM-V-4-gguf","kind":"GGUF"},{"id":"openbmb/MiniCPM-V-4-int4","kind":"INT4"},{"id":"openbmb/MiniCPM-V-4-AWQ","kind":"AWQ"},{"id":"openbmb/MiniCPM-V-4-GPTQ","kind":"GPTQ"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-V-4","u":"https://huggingface.co/openbmb/MiniCPM-V-4"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-V-4/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm-v-4"},{"id":"minicpm-v-4-6","name":"MiniCPM-V-4.6","hf":"openbmb/MiniCPM-V-4.6","org":"openbmb","family":"minicpm","series":"MiniCPM-V-4.6","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-04-13","updated":"2026-08-17","gated":false,"params":{"total":1.3,"active":null,"src":"safetensors","q":null,"stTotal":1.3},"moe":false,"ctx":262144,"arch":{"L":24,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4,"131072":1.61},"mem":{"bf16":{"w":2.6,"t":3.5},"fp8":{"w":1.38,"t":2.1},"q4":{"w":0.79,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.6,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"minicpm-v4.6","url":"https://ollama.com/library/minicpm-v4.6"}],"variants":[{"id":"openbmb/MiniCPM-V-4.6","kind":"main"},{"id":"openbmb/MiniCPM-V-4.6-BNB","kind":"main"},{"id":"openbmb/MiniCPM-V-4.6-GPTQ","kind":"GPTQ"},{"id":"openbmb/MiniCPM-V-4.6-AWQ","kind":"AWQ"},{"id":"openbmb/MiniCPM-V-4.6-gguf","kind":"GGUF"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-V-4.6","u":"https://huggingface.co/openbmb/MiniCPM-V-4.6"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-V-4.6/blob/main/config.json"},{"t":"Ollama library · minicpm-v4.6","u":"https://ollama.com/library/minicpm-v4.6"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm-v-4-6"},{"id":"minicpm-v-4-6-thinking","name":"MiniCPM-V-4.6-Thinking","hf":"openbmb/MiniCPM-V-4.6-Thinking","org":"openbmb","family":"minicpm","series":"MiniCPM-V-4.6-Thinking","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2026-05-08","updated":"2026-08-17","gated":false,"params":{"total":1.3,"active":null,"src":"safetensors","q":null,"stTotal":1.3},"moe":false,"ctx":262144,"arch":{"L":24,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4,"131072":1.61},"mem":{"bf16":{"w":2.6,"t":3.5},"fp8":{"w":1.38,"t":2.1},"q4":{"w":0.79,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.6,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM-V-4.6-Thinking","kind":"main"},{"id":"openbmb/MiniCPM-V-4.6-Thinking-BNB","kind":"main"},{"id":"openbmb/MiniCPM-V-4.6-Thinking-AWQ","kind":"AWQ"},{"id":"openbmb/MiniCPM-V-4.6-Thinking-GPTQ","kind":"GPTQ"},{"id":"openbmb/MiniCPM-V-4.6-Thinking-gguf","kind":"GGUF"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-V-4.6-Thinking","u":"https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm-v-4-6-thinking"},{"id":"minicpm-v-4-7-1b","name":"MiniCPM-V-4.7-1B","hf":"openbmb/MiniCPM-V-4.7-1B","org":"openbmb","family":"minicpm","series":"MiniCPM-V-4.7","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-10-06","updated":"2026-10-19","gated":false,"params":{"total":1.554,"active":null,"src":"safetensors","q":null,"stTotal":1.554},"moe":false,"ctx":262144,"arch":{"L":24,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4,"131072":1.61},"mem":{"bf16":{"w":3.11,"t":4},"fp8":{"w":1.65,"t":2.4},"q4":{"w":0.94,"t":1.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.11,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM-V-4.7-1B","kind":"main"},{"id":"openbmb/MiniCPM-V-4.7-1B-gguf","kind":"GGUF"},{"id":"openbmb/MiniCPM-V-4.7-1B-int4","kind":"INT4"},{"id":"openbmb/MiniCPM-V-4.7-1B-GPTQ","kind":"GPTQ"},{"id":"openbmb/MiniCPM-V-4.7-1B-AWQ","kind":"AWQ"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-V-4.7-1B","u":"https://huggingface.co/openbmb/MiniCPM-V-4.7-1B"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-V-4.7-1B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/minicpm-v-4-7-1b/"},{"id":"minicpm-v-4-7-35b-a3b","name":"MiniCPM-V-4.7-35B-A3B","hf":"openbmb/MiniCPM-V-4.7-35B-A3B","org":"openbmb","family":"minicpm","series":"MiniCPM-V-4.7","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-10-07","updated":"2026-10-19","gated":false,"params":{"total":35.213,"active":3,"src":"safetensors","q":null,"stTotal":35.213},"moe":true,"ctx":262144,"arch":{"L":40,"attn":10,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.17,"32768":0.67,"131072":2.68},"mem":{"bf16":{"w":70.43,"t":78.1},"fp8":{"w":37.41,"t":41.8},"q4":{"w":21.35,"t":24.2}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":70.43,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM-V-4.7-35B-A3B-gguf","kind":"GGUF"},{"id":"openbmb/MiniCPM-V-4.7-35B-A3B","kind":"main"},{"id":"openbmb/MiniCPM-V-4.7-35B-A3B-FP8","kind":"FP8"},{"id":"openbmb/MiniCPM-V-4.7-35B-A3B-int4","kind":"INT4"},{"id":"openbmb/MiniCPM-V-4.7-35B-A3B-GPTQ","kind":"GPTQ"},{"id":"openbmb/MiniCPM-V-4.7-35B-A3B-AWQ","kind":"AWQ"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-V-4.7-35B-A3B","u":"https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/minicpm-v-4-7-35b-a3b/"},{"id":"minicpm-v-4-5","name":"MiniCPM-V-4_5","hf":"openbmb/MiniCPM-V-4_5","org":"openbmb","family":"minicpm","series":"MiniCPM-V-4_5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-08-24","updated":"2026-08-18","gated":false,"params":{"total":8.696,"active":null,"src":"safetensors","q":null,"stTotal":8.696},"moe":false,"ctx":40960,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":17.39,"t":20.8},"fp8":{"w":9.24,"t":11.9},"q4":{"w":5.27,"t":7.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":17.39,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"minicpm-v4.5","url":"https://ollama.com/library/minicpm-v4.5"}],"variants":[{"id":"openbmb/MiniCPM-V-4_5","kind":"main"},{"id":"openbmb/MiniCPM-V-4_5-gguf","kind":"GGUF"},{"id":"openbmb/MiniCPM-V-4_5-AWQ","kind":"AWQ"},{"id":"openbmb/MiniCPM-V-4_5-int4","kind":"INT4"},{"id":"openbmb/MiniCPM-V-4_5-GPTQ","kind":"GPTQ"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-V-4_5","u":"https://huggingface.co/openbmb/MiniCPM-V-4_5"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-V-4_5/blob/main/config.json"},{"t":"Ollama library · minicpm-v4.5","u":"https://ollama.com/library/minicpm-v4.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm-v-4-5"},{"id":"minicpm-o-2-6","name":"MiniCPM-o-2_6","hf":"openbmb/MiniCPM-o-2_6","org":"openbmb","family":"minicpm","series":"MiniCPM-o-2_6","task":"omni","pipeline":"any-to-any","tags":[],"released":"2025-01-12","updated":"2026-08-18","gated":false,"params":{"total":8.675,"active":null,"src":"safetensors","q":null,"stTotal":8.675},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":17.35,"t":20.1},"fp8":{"w":9.22,"t":11.1},"q4":{"w":5.26,"t":6.8}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.35,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM-o-2_6","kind":"main"},{"id":"openbmb/MiniCPM-o-2_6-gguf","kind":"GGUF"},{"id":"openbmb/MiniCPM-o-2_6-int4","kind":"INT4"},{"id":"openbmb/MiniCPM-o-2_6-GPTQ","kind":"GPTQ"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-o-2_6","u":"https://huggingface.co/openbmb/MiniCPM-o-2_6"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-o-2_6/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm-o-2-6"},{"id":"minicpm-o-4-5","name":"MiniCPM-o-4_5","hf":"openbmb/MiniCPM-o-4_5","org":"openbmb","family":"minicpm","series":"MiniCPM-o-4_5","task":"omni","pipeline":"any-to-any","tags":[],"released":"2026-02-03","updated":"2026-10-16","gated":false,"params":{"total":9.372,"active":null,"src":"safetensors","q":null,"stTotal":9.372},"moe":false,"ctx":40960,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":18.74,"t":22.3},"fp8":{"w":9.96,"t":12.7},"q4":{"w":5.68,"t":8}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":18.74,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM-o-4_5","kind":"main"},{"id":"openbmb/MiniCPM-o-4_5-gguf","kind":"GGUF"},{"id":"openbmb/MiniCPM-o-4_5-awq","kind":"AWQ"},{"id":"openbmb/MiniCPM-o-4_5-GPTQ","kind":"GPTQ"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM-o-4_5","u":"https://huggingface.co/openbmb/MiniCPM-o-4_5"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM-o-4_5/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm-o-4-5"},{"id":"minicpm3-4b","name":"MiniCPM3-4B","hf":"openbmb/MiniCPM3-4B","org":"openbmb","family":"minicpm","series":"MiniCPM3","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-03","updated":"2025-02-27","gated":false,"params":{"total":4,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":32768,"arch":{"L":62,"attn":62,"slide":0,"win":null,"kvElems":288,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.29,"32768":1.17},"mem":{"bf16":{"w":8,"t":9.6},"fp8":{"w":4.25,"t":5.5},"q4":{"w":2.42,"t":3.5}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.15,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"openbmb/MiniCPM3-4B","kind":"main"},{"id":"openbmb/MiniCPM3-4B-GGUF","kind":"GGUF"},{"id":"openbmb/MiniCPM3-4B-GPTQ-Int4","kind":"GPTQ/INT4"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM3-4B","u":"https://huggingface.co/openbmb/MiniCPM3-4B"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM3-4B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm3-4b"},{"id":"minicpm4-0-5b","name":"MiniCPM4-0.5B","hf":"openbmb/MiniCPM4-0.5B","org":"openbmb","family":"minicpm","series":"MiniCPM4","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-05","updated":"2025-10-20","gated":false,"params":{"total":0.434,"active":null,"src":"safetensors","q":null,"stTotal":0.434},"moe":false,"ctx":32768,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":256,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":0.87,"t":1.6},"fp8":{"w":0.46,"t":1.1},"q4":{"w":0.26,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.87,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"openbmb/MiniCPM4-0.5B","kind":"main"},{"id":"openbmb/MiniCPM4-0.5B-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM4-0.5B","u":"https://huggingface.co/openbmb/MiniCPM4-0.5B"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM4-0.5B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm4-0-5b"},{"id":"minicpm4-8b","name":"MiniCPM4-8B","hf":"openbmb/MiniCPM4-8B","org":"openbmb","family":"minicpm","series":"MiniCPM4","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-05","updated":"2025-10-24","gated":false,"params":{"total":8.185,"active":null,"src":"safetensors","q":null,"stTotal":8.185},"moe":false,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.27,"32768":1.07},"mem":{"bf16":{"w":16.37,"t":18.8},"fp8":{"w":8.7,"t":10.3},"q4":{"w":4.96,"t":6.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.37,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"}],"variants":[{"id":"openbmb/MiniCPM4-8B","kind":"main"},{"id":"openbmb/MiniCPM4-8B-GGUF","kind":"GGUF"},{"id":"openbmb/MiniCPM4-8B-mlx","kind":"MLX"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM4-8B","u":"https://huggingface.co/openbmb/MiniCPM4-8B"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM4-8B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm4-8b"},{"id":"minicpm4-mcp","name":"MiniCPM4-MCP","hf":"openbmb/MiniCPM4-MCP","org":"openbmb","family":"minicpm","series":"MiniCPM4-MCP","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-05","updated":"2025-06-10","gated":false,"params":{"total":8.185,"active":null,"src":"safetensors","q":null,"stTotal":8.185},"moe":false,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.27,"32768":1.07},"mem":{"bf16":{"w":16.37,"t":18.8},"fp8":{"w":8.7,"t":10.3},"q4":{"w":4.96,"t":6.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.37,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM4-MCP","kind":"main"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM4-MCP","u":"https://huggingface.co/openbmb/MiniCPM4-MCP"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM4-MCP/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm4-mcp"},{"id":"minicpm4-1-8b","name":"MiniCPM4.1-8B","hf":"openbmb/MiniCPM4.1-8B","org":"openbmb","family":"minicpm","series":"MiniCPM4.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-02","updated":"2025-10-24","gated":false,"params":{"total":8.185,"active":null,"src":"safetensors","q":null,"stTotal":8.185},"moe":false,"ctx":65536,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.27,"32768":1.07},"mem":{"bf16":{"w":16.37,"t":18.8},"fp8":{"w":8.7,"t":10.3},"q4":{"w":4.96,"t":6.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.37,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM4.1-8B","kind":"main"},{"id":"openbmb/MiniCPM4.1-8B-GGUF","kind":"GGUF"},{"id":"openbmb/MiniCPM4.1-8B-GPTQ","kind":"GPTQ"},{"id":"openbmb/MiniCPM4.1-8B-MLX","kind":"MLX"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM4.1-8B","u":"https://huggingface.co/openbmb/MiniCPM4.1-8B"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM4.1-8B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm4-1-8b"},{"id":"minicpm5-1b","name":"MiniCPM5-1B","hf":"openbmb/MiniCPM5-1B","org":"openbmb","family":"minicpm","series":"MiniCPM5","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-05-21","updated":"2026-08-17","gated":false,"params":{"total":1.081,"active":null,"src":"safetensors","q":null,"stTotal":1.081},"moe":false,"ctx":131072,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.2,"32768":0.81,"131072":3.22},"mem":{"bf16":{"w":2.16,"t":3.1},"fp8":{"w":1.15,"t":2},"q4":{"w":0.66,"t":1.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.16,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM5-1B","kind":"main"},{"id":"openbmb/MiniCPM5-1B-GGUF","kind":"GGUF"},{"id":"openbmb/MiniCPM5-1B-MLX","kind":"MLX"},{"id":"openbmb/MiniCPM5-1B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM5-1B","u":"https://huggingface.co/openbmb/MiniCPM5-1B"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM5-1B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-minicpm5-1b"},{"id":"minicpm5-2b","name":"MiniCPM5-2B","hf":"openbmb/MiniCPM5-2B","org":"openbmb","family":"minicpm","series":"MiniCPM5","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-09-06","updated":"2026-09-29","gated":false,"params":{"total":2.517,"active":null,"src":"safetensors","q":null,"stTotal":2.517},"moe":false,"ctx":131072,"arch":{"L":42,"attn":42,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.35,"32768":1.41,"131072":5.64},"mem":{"bf16":{"w":5.03,"t":6.4},"fp8":{"w":2.67,"t":3.8},"q4":{"w":1.53,"t":2.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.03,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"openbmb/MiniCPM5-2B","kind":"main"},{"id":"openbmb/MiniCPM5-2B-MLX","kind":"MLX"},{"id":"openbmb/MiniCPM5-2B-GGUF","kind":"GGUF"},{"id":"openbmb/MiniCPM5-2B-Base","kind":"Base"},{"id":"openbmb/MiniCPM5-2B-GPTQ","kind":"GPTQ"}],"sources":[{"t":"Hugging Face · openbmb/MiniCPM5-2B","u":"https://huggingface.co/openbmb/MiniCPM5-2B"},{"t":"config.json","u":"https://huggingface.co/openbmb/MiniCPM5-2B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/minicpm5-2b/"},{"id":"voxcpm-0-5b","name":"VoxCPM-0.5B","hf":"openbmb/VoxCPM-0.5B","org":"openbmb","family":"minicpm","series":"VoxCPM","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2025-09-16","updated":"2026-08-18","gated":false,"params":{"total":0.5,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1,"t":1.6},"fp8":{"w":0.53,"t":1.1},"q4":{"w":0.3,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.61,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"openbmb/VoxCPM-0.5B","kind":"main"}],"sources":[{"t":"Hugging Face · openbmb/VoxCPM-0.5B","u":"https://huggingface.co/openbmb/VoxCPM-0.5B"},{"t":"config.json","u":"https://huggingface.co/openbmb/VoxCPM-0.5B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-voxcpm-0-5b"},{"id":"voxcpm1-5","name":"VoxCPM1.5","hf":"openbmb/VoxCPM1.5","org":"openbmb","family":"minicpm","series":"VoxCPM1.5","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2025-12-05","updated":"2026-08-18","gated":false,"params":{"total":0.802,"active":null,"src":"safetensors","q":null,"stTotal":0.802},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.6,"t":2.3},"fp8":{"w":0.85,"t":1.4},"q4":{"w":0.49,"t":1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.6,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"openbmb/VoxCPM1.5","kind":"main"}],"sources":[{"t":"Hugging Face · openbmb/VoxCPM1.5","u":"https://huggingface.co/openbmb/VoxCPM1.5"},{"t":"config.json","u":"https://huggingface.co/openbmb/VoxCPM1.5/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-voxcpm1-5"},{"id":"voxcpm2","name":"VoxCPM2","hf":"openbmb/VoxCPM2","org":"openbmb","family":"minicpm","series":"VoxCPM2","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2026-04-03","updated":"2026-08-18","gated":false,"params":{"total":2.29,"active":null,"src":"safetensors","q":null,"stTotal":2.29},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":4.58,"t":5.5},"fp8":{"w":2.43,"t":3.2},"q4":{"w":1.39,"t":2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.58,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"}],"variants":[{"id":"openbmb/VoxCPM2","kind":"main"}],"sources":[{"t":"Hugging Face · openbmb/VoxCPM2","u":"https://huggingface.co/openbmb/VoxCPM2"},{"t":"config.json","u":"https://huggingface.co/openbmb/VoxCPM2/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/minicpm/#m-voxcpm2"},{"id":"minimax-h3","name":"MiniMax-H3","hf":"MiniMaxAI/MiniMax-H3","org":"MiniMaxAI","family":"minimax","series":"MiniMax-H3","task":"video","pipeline":"image-text-to-video","tags":[],"released":"2026-07-28","updated":"2026-08-13","gated":false,"params":{"total":33.123,"active":null,"src":"safetensors","q":null,"stTotal":33.123},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":66.25,"t":73.4},"fp8":{"w":35.19,"t":39.2},"q4":{"w":20.08,"t":22.6}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":498.33,"native":"BF16","license":{"id":"minimax-h3-community-license-agreement","name":"minimax-h3-community-license-agreement","link":"https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"MiniMaxAI/MiniMax-H3","kind":"main"}],"sources":[{"t":"Hugging Face · MiniMaxAI/MiniMax-H3","u":"https://huggingface.co/MiniMaxAI/MiniMax-H3"},{"t":"License","u":"https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/minimax/#m-minimax-h3"},{"id":"minimax-m1-40k","name":"MiniMax-M1-40k","hf":"MiniMaxAI/MiniMax-M1-40k","org":"MiniMaxAI","family":"minimax","series":"MiniMax-M1-40k","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-05","updated":"2025-07-07","gated":false,"params":{"total":456,"active":45.9,"src":"card","q":"a total of 456 billion parameters with 45.9 billion parameters activated","stTotal":456.09},"moe":true,"ctx":null,"arch":{"L":80,"attn":10,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.34,"32768":1.34,"131072":5.37},"mem":{"bf16":{"w":912,"t":1004},"fp8":{"w":484.5,"t":533.8},"q4":{"w":276.45,"t":304.9}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":912.21,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/MiniMaxAI/MiniMax-M1-40k/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"MiniMaxAI/MiniMax-M1-40k","kind":"main"},{"id":"MiniMaxAI/MiniMax-M1-40k-hf","kind":"HF-transformers"}],"sources":[{"t":"Hugging Face · MiniMaxAI/MiniMax-M1-40k","u":"https://huggingface.co/MiniMaxAI/MiniMax-M1-40k"},{"t":"config.json","u":"https://huggingface.co/MiniMaxAI/MiniMax-M1-40k/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/MiniMaxAI/MiniMax-M1-40k/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/minimax-m1-40k/"},{"id":"minimax-m1-80k","name":"MiniMax-M1-80k","hf":"MiniMaxAI/MiniMax-M1-80k","org":"MiniMaxAI","family":"minimax","series":"MiniMax-M1-80k","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-13","updated":"2025-07-07","gated":false,"params":{"total":456,"active":45.9,"src":"card","q":"a total of 456 billion parameters with 45.9 billion parameters activated","stTotal":456.09},"moe":true,"ctx":null,"arch":{"L":80,"attn":10,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.34,"32768":1.34,"131072":5.37},"mem":{"bf16":{"w":912,"t":1004},"fp8":{"w":484.5,"t":533.8},"q4":{"w":276.45,"t":304.9}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":912.21,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/MiniMaxAI/MiniMax-M1-80k/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"MiniMaxAI/MiniMax-M1-80k","kind":"main"},{"id":"MiniMaxAI/MiniMax-M1-80k-hf","kind":"HF-transformers"}],"sources":[{"t":"Hugging Face · MiniMaxAI/MiniMax-M1-80k","u":"https://huggingface.co/MiniMaxAI/MiniMax-M1-80k"},{"t":"config.json","u":"https://huggingface.co/MiniMaxAI/MiniMax-M1-80k/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/MiniMaxAI/MiniMax-M1-80k/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/minimax-m1-80k/"},{"id":"minimax-m2","name":"MiniMax-M2","hf":"MiniMaxAI/MiniMax-M2","org":"MiniMaxAI","family":"minimax","series":"MiniMax-M2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-10-22","updated":"2025-12-23","gated":false,"params":{"total":230,"active":10,"src":"card","q":"230 billion total parameters with 10 billion active parameters","stTotal":228.69},"moe":true,"ctx":196608,"arch":{"L":62,"attn":62,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.08,"32768":8.32,"131072":33.29},"mem":{"bf16":{"w":460,"t":508.6},"fp8":{"w":244.38,"t":271.4},"q4":{"w":139.44,"t":156}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":230.13,"native":"F8_E4M3","license":{"id":"modified-mit","name":"modified-mit","link":"https://github.com/MiniMax-AI/MiniMax-M2/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"MiniMaxAI/MiniMax-M2","kind":"main"}],"sources":[{"t":"Hugging Face · MiniMaxAI/MiniMax-M2","u":"https://huggingface.co/MiniMaxAI/MiniMax-M2"},{"t":"config.json","u":"https://huggingface.co/MiniMaxAI/MiniMax-M2/blob/main/config.json"},{"t":"License","u":"https://github.com/MiniMax-AI/MiniMax-M2/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/minimax-m2/"},{"id":"minimax-m2-1","name":"MiniMax-M2.1","hf":"MiniMaxAI/MiniMax-M2.1","org":"MiniMaxAI","family":"minimax","series":"MiniMax-M2.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-12-20","updated":"2026-02-13","gated":false,"params":{"total":228.69,"active":null,"src":"safetensors","q":null,"stTotal":228.69},"moe":true,"ctx":196608,"arch":{"L":62,"attn":62,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.08,"32768":8.32,"131072":33.29},"mem":{"bf16":{"w":457.38,"t":505.7},"fp8":{"w":242.98,"t":269.9},"q4":{"w":138.64,"t":155.1}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":230.13,"native":"F8_E4M3","license":{"id":"modified-mit","name":"modified-mit","link":"https://github.com/MiniMax-AI/MiniMax-M2.1/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"MiniMaxAI/MiniMax-M2.1","kind":"main"}],"sources":[{"t":"Hugging Face · MiniMaxAI/MiniMax-M2.1","u":"https://huggingface.co/MiniMaxAI/MiniMax-M2.1"},{"t":"config.json","u":"https://huggingface.co/MiniMaxAI/MiniMax-M2.1/blob/main/config.json"},{"t":"License","u":"https://github.com/MiniMax-AI/MiniMax-M2.1/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/minimax-m2-1/"},{"id":"minimax-m2-5","name":"MiniMax-M2.5","hf":"MiniMaxAI/MiniMax-M2.5","org":"MiniMaxAI","family":"minimax","series":"MiniMax-M2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-02-12","updated":"2026-03-10","gated":false,"params":{"total":228.69,"active":null,"src":"safetensors","q":null,"stTotal":228.69},"moe":true,"ctx":196608,"arch":{"L":62,"attn":62,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.08,"32768":8.32,"131072":33.29},"mem":{"bf16":{"w":457.38,"t":505.7},"fp8":{"w":242.98,"t":269.9},"q4":{"w":138.64,"t":155.1}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":230.13,"native":"F8_E4M3","license":{"id":"modified-mit","name":"modified-mit","link":"https://github.com/MiniMax-AI/MiniMax-M2.5/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"MiniMaxAI/MiniMax-M2.5","kind":"main"}],"sources":[{"t":"Hugging Face · MiniMaxAI/MiniMax-M2.5","u":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5"},{"t":"config.json","u":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5/blob/main/config.json"},{"t":"License","u":"https://github.com/MiniMax-AI/MiniMax-M2.5/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/minimax-m2-5/"},{"id":"minimax-m2-7","name":"MiniMax-M2.7","hf":"MiniMaxAI/MiniMax-M2.7","org":"MiniMaxAI","family":"minimax","series":"MiniMax-M2.7","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-09","updated":"2026-04-20","gated":false,"params":{"total":228.69,"active":null,"src":"safetensors","q":null,"stTotal":228.69},"moe":true,"ctx":204800,"arch":{"L":62,"attn":62,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.08,"32768":8.32,"131072":33.29},"mem":{"bf16":{"w":457.38,"t":505.7},"fp8":{"w":242.98,"t":269.9},"q4":{"w":138.64,"t":155.1}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":230.13,"native":"F8_E4M3","license":{"id":"other","name":"other","link":"https://github.com/MiniMax-AI/MiniMax-M2.7/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"MiniMaxAI/MiniMax-M2.7","kind":"main"}],"sources":[{"t":"Hugging Face · MiniMaxAI/MiniMax-M2.7","u":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7"},{"t":"config.json","u":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/config.json"},{"t":"License","u":"https://github.com/MiniMax-AI/MiniMax-M2.7/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/minimax-m2-7/"},{"id":"minimax-m3","name":"MiniMax-M3","hf":"MiniMaxAI/MiniMax-M3","org":"MiniMaxAI","family":"minimax","series":"MiniMax-M3","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-06-02","updated":"2026-07-23","gated":false,"params":{"total":428,"active":23,"src":"card","q":"~428B parameters and ~23B activated parameters","stTotal":427.04},"moe":true,"ctx":1048576,"arch":{"L":60,"attn":60,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":["sparse_attention_config"]},"kv":null,"mem":{"bf16":{"w":856,"t":942.1},"fp8":{"w":454.75,"t":500.7},"q4":{"w":259.47,"t":285.9}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":854.18,"native":"BF16","license":{"id":"minimax-community","name":"minimax-community","link":"https://huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"MiniMaxAI/MiniMax-M3","kind":"main"},{"id":"MiniMaxAI/MiniMax-M3-MXFP8","kind":"main"}],"sources":[{"t":"Hugging Face · MiniMaxAI/MiniMax-M3","u":"https://huggingface.co/MiniMaxAI/MiniMax-M3"},{"t":"config.json","u":"https://huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/minimax-m3/"},{"id":"minimax-music3","name":"MiniMax-Music3","hf":"MiniMaxAI/MiniMax-Music3","org":"MiniMaxAI","family":"minimax","series":"MiniMax-Music3","task":"tts","pipeline":"text-to-audio","tags":[],"released":"2026-08-07","updated":"2026-08-14","gated":false,"params":{"total":2.432,"active":null,"src":"safetensors","q":null,"stTotal":2.432},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":4.86,"t":5.9},"fp8":{"w":2.58,"t":3.3},"q4":{"w":1.47,"t":2.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":46.97,"native":"F32","license":{"id":null,"name":null,"link":"https://huggingface.co/MiniMaxAI/MiniMax-Music3/blob/main/LICENSE","cls":"unknown"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"MiniMaxAI/MiniMax-Music3","kind":"main"}],"sources":[{"t":"Hugging Face · MiniMaxAI/MiniMax-Music3","u":"https://huggingface.co/MiniMaxAI/MiniMax-Music3"},{"t":"config.json","u":"https://huggingface.co/MiniMaxAI/MiniMax-Music3/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/MiniMaxAI/MiniMax-Music3/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/minimax/#m-minimax-music3"},{"id":"minimax-text-01-hf","name":"MiniMax-Text-01-hf","hf":"MiniMaxAI/MiniMax-Text-01-hf","org":"MiniMaxAI","family":"minimax","series":"MiniMax-Text-01","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-03","updated":"2025-07-09","gated":false,"params":{"total":456,"active":45.9,"src":"card","q":"456 billion total parameters, of which 45.9 billion are activated per token","stTotal":456.09},"moe":true,"ctx":4000000,"arch":{"L":80,"attn":10,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.34,"32768":1.34,"131072":5.37},"mem":{"bf16":{"w":912,"t":1004},"fp8":{"w":484.5,"t":533.8},"q4":{"w":276.45,"t":304.9}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":914.67,"native":"BF16","license":{"id":"minimax","name":"minimax","link":"https://huggingface.co/MiniMaxAI/MiniMax-Text-01-hf/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"MiniMaxAI/MiniMax-Text-01-hf","kind":"HF-transformers"},{"id":"MiniMaxAI/MiniMax-Text-01","kind":"main"}],"sources":[{"t":"Hugging Face · MiniMaxAI/MiniMax-Text-01-hf","u":"https://huggingface.co/MiniMaxAI/MiniMax-Text-01-hf"},{"t":"config.json","u":"https://huggingface.co/MiniMaxAI/MiniMax-Text-01-hf/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/MiniMaxAI/MiniMax-Text-01-hf/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/minimax-text-01-hf/"},{"id":"minimax-vl-01","name":"MiniMax-VL-01","hf":"MiniMaxAI/MiniMax-VL-01","org":"MiniMaxAI","family":"minimax","series":"MiniMax-VL-01","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-01-12","updated":"2025-07-03","gated":false,"params":{"total":456.437,"active":null,"src":"safetensors","q":null,"stTotal":456.437},"moe":true,"ctx":8192,"arch":{"L":80,"attn":10,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.34},"mem":{"bf16":{"w":912.87,"t":1005},"fp8":{"w":484.96,"t":534.3},"q4":{"w":276.71,"t":305.2}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":915.37,"native":"BF16","license":{"id":null,"name":null,"link":null,"cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"MiniMaxAI/MiniMax-VL-01","kind":"main"}],"sources":[{"t":"Hugging Face · MiniMaxAI/MiniMax-VL-01","u":"https://huggingface.co/MiniMaxAI/MiniMax-VL-01"},{"t":"config.json","u":"https://huggingface.co/MiniMaxAI/MiniMax-VL-01/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/minimax-vl-01/"},{"id":"codestral-22b-v0-1","name":"Codestral-22B-v0.1","hf":"mistralai/Codestral-22B-v0.1","org":"mistralai","family":"mistral","series":"Codestral","task":"llm","pipeline":null,"tags":["coding"],"released":"2024-05-29","updated":"2025-07-24","gated":false,"params":{"total":22.247,"active":null,"src":"safetensors","q":null,"stTotal":22.247},"moe":false,"ctx":32768,"arch":{"L":56,"attn":56,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.88,"32768":7.52},"mem":{"bf16":{"w":44.49,"t":51.3},"fp8":{"w":23.64,"t":28.4},"q4":{"w":13.49,"t":17.2}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":88.99,"native":"BF16","license":{"id":"mnpl","name":"Mistral Non-Production License","link":"https://mistral.ai/licences/MNPL-0.1.md","cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Codestral-22B-v0.1","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Codestral-22B-v0.1","u":"https://huggingface.co/mistralai/Codestral-22B-v0.1"},{"t":"config.json","u":"https://huggingface.co/mistralai/Codestral-22B-v0.1/blob/main/config.json"},{"t":"License","u":"https://mistral.ai/licences/MNPL-0.1.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-codestral-22b-v0-1"},{"id":"devstral-2-123b-instruct-2512","name":"Devstral-2-123B-Instruct-2512","hf":"mistralai/Devstral-2-123B-Instruct-2512","org":"mistralai","family":"mistral","series":"Devstral-2","task":"llm","pipeline":null,"tags":["coding"],"released":"2025-11-28","updated":"2026-07-15","gated":false,"params":{"total":125.026,"active":null,"src":"safetensors","q":null,"stTotal":125.026},"moe":false,"ctx":262144,"arch":{"L":88,"attn":88,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.95,"32768":11.81,"131072":47.24},"mem":{"bf16":{"w":250.05,"t":278.5},"fp8":{"w":132.84,"t":149.6},"q4":{"w":75.8,"t":86.8}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"h200","mac":"mac256"}},"disk":256.5,"native":"F8_E4M3","license":{"id":"other","name":"other","link":"https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Devstral-2-123B-Instruct-2512","kind":"Instruct"}],"sources":[{"t":"Hugging Face · mistralai/Devstral-2-123B-Instruct-2512","u":"https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"},{"t":"config.json","u":"https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/devstral-2-123b-instruct-2512/"},{"id":"devstral-small-2505","name":"Devstral-Small-2505","hf":"mistralai/Devstral-Small-2505","org":"mistralai","family":"mistral","series":"Devstral-Small","task":"llm","pipeline":null,"tags":["coding"],"released":"2025-05-12","updated":"2025-08-18","gated":false,"params":{"total":23.572,"active":null,"src":"safetensors","q":null,"stTotal":23.572},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":47.14,"t":53.7},"fp8":{"w":25.05,"t":29.4},"q4":{"w":14.29,"t":17.6}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":94.29,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Devstral-Small-2505_gguf","kind":"GGUF"},{"id":"mistralai/Devstral-Small-2505","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Devstral-Small-2505","u":"https://huggingface.co/mistralai/Devstral-Small-2505"},{"t":"config.json","u":"https://huggingface.co/mistralai/Devstral-Small-2505/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-devstral-small-2505"},{"id":"devstral-small-2507","name":"Devstral-Small-2507","hf":"mistralai/Devstral-Small-2507","org":"mistralai","family":"mistral","series":"Devstral-Small","task":"llm","pipeline":null,"tags":["coding"],"released":"2025-07-04","updated":"2025-08-18","gated":false,"params":{"total":23.572,"active":null,"src":"safetensors","q":null,"stTotal":23.572},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":47.14,"t":53.7},"fp8":{"w":25.05,"t":29.4},"q4":{"w":14.29,"t":17.6}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":94.29,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Devstral-Small-2507_gguf","kind":"GGUF"},{"id":"mistralai/Devstral-Small-2507","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Devstral-Small-2507","u":"https://huggingface.co/mistralai/Devstral-Small-2507"},{"t":"config.json","u":"https://huggingface.co/mistralai/Devstral-Small-2507/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-devstral-small-2507"},{"id":"lidstral-arabic","name":"LIDstral-Arabic","hf":"mistralai/LIDstral-Arabic","org":"mistralai","family":"mistral","series":"LIDstral-Arabic","task":"llm","pipeline":"text-classification","tags":[],"released":"2026-10-08","updated":"2026-10-13","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":1.07,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"mistralai/LIDstral-Arabic","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/LIDstral-Arabic","u":"https://huggingface.co/mistralai/LIDstral-Arabic"}],"page":"https://aimap.page/en/models/compute/open-models/lidstral-arabic/"},{"id":"magistral-small-2506","name":"Magistral-Small-2506","hf":"mistralai/Magistral-Small-2506","org":"mistralai","family":"mistral","series":"Magistral-Small","task":"llm","pipeline":null,"tags":["reasoning"],"released":"2025-06-04","updated":"2025-07-28","gated":false,"params":{"total":23.572,"active":null,"src":"safetensors","q":null,"stTotal":23.572},"moe":false,"ctx":40960,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37},"mem":{"bf16":{"w":47.14,"t":53.7},"fp8":{"w":25.05,"t":29.4},"q4":{"w":14.29,"t":17.6}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":94.29,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"}],"variants":[{"id":"mistralai/Magistral-Small-2506","kind":"main"},{"id":"mistralai/Magistral-Small-2506_gguf","kind":"GGUF"}],"sources":[{"t":"Hugging Face · mistralai/Magistral-Small-2506","u":"https://huggingface.co/mistralai/Magistral-Small-2506"},{"t":"config.json","u":"https://huggingface.co/mistralai/Magistral-Small-2506/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-magistral-small-2506"},{"id":"magistral-small-2507","name":"Magistral-Small-2507","hf":"mistralai/Magistral-Small-2507","org":"mistralai","family":"mistral","series":"Magistral-Small","task":"llm","pipeline":null,"tags":["reasoning"],"released":"2025-07-18","updated":"2025-12-22","gated":false,"params":{"total":23.572,"active":null,"src":"safetensors","q":null,"stTotal":23.572},"moe":false,"ctx":40960,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37},"mem":{"bf16":{"w":47.14,"t":53.7},"fp8":{"w":25.05,"t":29.4},"q4":{"w":14.29,"t":17.6}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":94.29,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Magistral-Small-2507","kind":"main"},{"id":"mistralai/Magistral-Small-2507-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · mistralai/Magistral-Small-2507","u":"https://huggingface.co/mistralai/Magistral-Small-2507"},{"t":"config.json","u":"https://huggingface.co/mistralai/Magistral-Small-2507/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-magistral-small-2507"},{"id":"magistral-small-2509","name":"Magistral-Small-2509","hf":"mistralai/Magistral-Small-2509","org":"mistralai","family":"mistral","series":"Magistral-Small","task":"llm","pipeline":null,"tags":["reasoning"],"released":"2025-09-12","updated":"2026-02-23","gated":false,"params":{"total":24.011,"active":null,"src":"safetensors","q":null,"stTotal":24.011},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":48.02,"t":54.7},"fp8":{"w":25.51,"t":29.9},"q4":{"w":14.56,"t":17.9}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":96.05,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Magistral-Small-2509","kind":"main"},{"id":"mistralai/Magistral-Small-2509-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · mistralai/Magistral-Small-2509","u":"https://huggingface.co/mistralai/Magistral-Small-2509"},{"t":"config.json","u":"https://huggingface.co/mistralai/Magistral-Small-2509/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-magistral-small-2509"},{"id":"ministral-8b-instruct-2410","name":"Ministral-8B-Instruct-2410","hf":"mistralai/Ministral-8B-Instruct-2410","org":"mistralai","family":"mistral","series":"Ministral","task":"llm","pipeline":null,"tags":[],"released":"2024-10-15","updated":"2025-07-31","gated":false,"params":{"total":8.02,"active":null,"src":"safetensors","q":null,"stTotal":8.02},"moe":false,"ctx":32768,"arch":{"L":36,"attn":9,"slide":27,"win":32768,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":16.04,"t":19.4},"fp8":{"w":8.52,"t":11.1},"q4":{"w":4.86,"t":7.1}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":32.08,"native":"BF16","license":{"id":"mrl","name":"Mistral Research License","link":"https://mistral.ai/licenses/MRL-0.1.md","cls":"nc"},"runtimes":[{"id":"vllm","via":"card"}],"variants":[{"id":"mistralai/Ministral-8B-Instruct-2410","kind":"Instruct"}],"sources":[{"t":"Hugging Face · mistralai/Ministral-8B-Instruct-2410","u":"https://huggingface.co/mistralai/Ministral-8B-Instruct-2410"},{"t":"config.json","u":"https://huggingface.co/mistralai/Ministral-8B-Instruct-2410/blob/main/config.json"},{"t":"License","u":"https://mistral.ai/licenses/MRL-0.1.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-ministral-8b-instruct-2410"},{"id":"ministral-3-3b-instruct-2512-bf16","name":"Ministral-3-3B-Instruct-2512-BF16","hf":"mistralai/Ministral-3-3B-Instruct-2512-BF16","org":"mistralai","family":"mistral","series":"Ministral-3","task":"llm","pipeline":null,"tags":[],"released":"2025-10-31","updated":"2026-07-15","gated":false,"params":{"total":4.252,"active":null,"src":"safetensors","q":null,"stTotal":4.252},"moe":false,"ctx":262144,"arch":{"L":26,"attn":26,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.87,"32768":3.49,"131072":13.96},"mem":{"bf16":{"w":8.5,"t":10.7},"fp8":{"w":4.52,"t":6.3},"q4":{"w":2.58,"t":4.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.4,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"mistralai/Ministral-3-3B-Instruct-2512","kind":"Instruct"},{"id":"mistralai/Ministral-3-3B-Instruct-2512-GGUF","kind":"Instruct/GGUF"},{"id":"mistralai/Ministral-3-3B-Instruct-2512-BF16","kind":"Instruct/BF16"},{"id":"mistralai/Ministral-3-3B-Base-2512","kind":"Base"},{"id":"mistralai/Ministral-3-3B-Instruct-2512-ONNX","kind":"Instruct/ONNX"}],"sources":[{"t":"Hugging Face · mistralai/Ministral-3-3B-Instruct-2512-BF16","u":"https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512-BF16"},{"t":"config.json","u":"https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512-BF16/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-ministral-3-3b-instruct-2512-bf16"},{"id":"ministral-3-8b-instruct-2512-bf16","name":"Ministral-3-8B-Instruct-2512-BF16","hf":"mistralai/Ministral-3-8B-Instruct-2512-BF16","org":"mistralai","family":"mistral","series":"Ministral-3","task":"llm","pipeline":null,"tags":[],"released":"2025-10-31","updated":"2026-07-15","gated":false,"params":{"total":8.918,"active":null,"src":"safetensors","q":null,"stTotal":8.918},"moe":false,"ctx":262144,"arch":{"L":34,"attn":34,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.14,"32768":4.56,"131072":18.25},"mem":{"bf16":{"w":17.84,"t":21.3},"fp8":{"w":9.48,"t":12.1},"q4":{"w":5.41,"t":7.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":35.67,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"mistralai/Ministral-3-8B-Instruct-2512","kind":"Instruct"},{"id":"mistralai/Ministral-3-8B-Instruct-2512-GGUF","kind":"Instruct/GGUF"},{"id":"mistralai/Ministral-3-8B-Instruct-2512-BF16","kind":"Instruct/BF16"},{"id":"mistralai/Ministral-3-8B-Base-2512","kind":"Base"}],"sources":[{"t":"Hugging Face · mistralai/Ministral-3-8B-Instruct-2512-BF16","u":"https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512-BF16"},{"t":"config.json","u":"https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512-BF16/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-ministral-3-8b-instruct-2512-bf16"},{"id":"ministral-3-14b-instruct-2512-bf16","name":"Ministral-3-14B-Instruct-2512-BF16","hf":"mistralai/Ministral-3-14B-Instruct-2512-BF16","org":"mistralai","family":"mistral","series":"Ministral-3","task":"llm","pipeline":null,"tags":[],"released":"2025-10-31","updated":"2026-07-15","gated":false,"params":{"total":13.945,"active":null,"src":"safetensors","q":null,"stTotal":13.945},"moe":false,"ctx":262144,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":27.89,"t":32.5},"fp8":{"w":14.82,"t":18.1},"q4":{"w":8.45,"t":11.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":55.78,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"mistralai/Ministral-3-14B-Instruct-2512","kind":"Instruct"},{"id":"mistralai/Ministral-3-14B-Instruct-2512-BF16","kind":"Instruct/BF16"},{"id":"mistralai/Ministral-3-14B-Instruct-2512-GGUF","kind":"Instruct/GGUF"},{"id":"mistralai/Ministral-3-14B-Base-2512","kind":"Base"}],"sources":[{"t":"Hugging Face · mistralai/Ministral-3-14B-Instruct-2512-BF16","u":"https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512-BF16"},{"t":"config.json","u":"https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512-BF16/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-ministral-3-14b-instruct-2512-bf16"},{"id":"ministral-3-3b-reasoning-2512","name":"Ministral-3-3B-Reasoning-2512","hf":"mistralai/Ministral-3-3B-Reasoning-2512","org":"mistralai","family":"mistral","series":"Ministral-3-Reasoning","task":"llm","pipeline":null,"tags":["reasoning"],"released":"2025-10-31","updated":"2026-07-15","gated":false,"params":{"total":4.252,"active":null,"src":"safetensors","q":null,"stTotal":4.252},"moe":false,"ctx":262144,"arch":{"L":26,"attn":26,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.87,"32768":3.49,"131072":13.96},"mem":{"bf16":{"w":8.5,"t":10.7},"fp8":{"w":4.52,"t":6.3},"q4":{"w":2.58,"t":4.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.4,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"mistralai/Ministral-3-3B-Reasoning-2512","kind":"main"},{"id":"mistralai/Ministral-3-3B-Reasoning-2512-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · mistralai/Ministral-3-3B-Reasoning-2512","u":"https://huggingface.co/mistralai/Ministral-3-3B-Reasoning-2512"},{"t":"config.json","u":"https://huggingface.co/mistralai/Ministral-3-3B-Reasoning-2512/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-ministral-3-3b-reasoning-2512"},{"id":"ministral-3-8b-reasoning-2512","name":"Ministral-3-8B-Reasoning-2512","hf":"mistralai/Ministral-3-8B-Reasoning-2512","org":"mistralai","family":"mistral","series":"Ministral-3-Reasoning","task":"llm","pipeline":null,"tags":["reasoning"],"released":"2025-10-31","updated":"2026-07-15","gated":false,"params":{"total":8.918,"active":null,"src":"safetensors","q":null,"stTotal":8.918},"moe":false,"ctx":262144,"arch":{"L":34,"attn":34,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.14,"32768":4.56,"131072":18.25},"mem":{"bf16":{"w":17.84,"t":21.3},"fp8":{"w":9.48,"t":12.1},"q4":{"w":5.41,"t":7.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":35.67,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"mistralai/Ministral-3-8B-Reasoning-2512","kind":"main"},{"id":"mistralai/Ministral-3-8B-Reasoning-2512-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · mistralai/Ministral-3-8B-Reasoning-2512","u":"https://huggingface.co/mistralai/Ministral-3-8B-Reasoning-2512"},{"t":"config.json","u":"https://huggingface.co/mistralai/Ministral-3-8B-Reasoning-2512/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-ministral-3-8b-reasoning-2512"},{"id":"ministral-3-14b-reasoning-2512","name":"Ministral-3-14B-Reasoning-2512","hf":"mistralai/Ministral-3-14B-Reasoning-2512","org":"mistralai","family":"mistral","series":"Ministral-3-Reasoning","task":"llm","pipeline":null,"tags":["reasoning"],"released":"2025-10-31","updated":"2026-07-15","gated":false,"params":{"total":13.945,"active":null,"src":"safetensors","q":null,"stTotal":13.945},"moe":false,"ctx":262144,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":27.89,"t":32.5},"fp8":{"w":14.82,"t":18.1},"q4":{"w":8.45,"t":11.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":55.78,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"mistralai/Ministral-3-14B-Reasoning-2512","kind":"main"},{"id":"mistralai/Ministral-3-14B-Reasoning-2512-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · mistralai/Ministral-3-14B-Reasoning-2512","u":"https://huggingface.co/mistralai/Ministral-3-14B-Reasoning-2512"},{"t":"config.json","u":"https://huggingface.co/mistralai/Ministral-3-14B-Reasoning-2512/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-ministral-3-14b-reasoning-2512"},{"id":"mistral-7b-instruct-v0-3","name":"Mistral-7B-Instruct-v0.3","hf":"mistralai/Mistral-7B-Instruct-v0.3","org":"mistralai","family":"mistral","series":"Mistral","task":"llm","pipeline":null,"tags":[],"released":"2024-05-22","updated":"2025-12-03","gated":false,"params":{"total":7.248,"active":null,"src":"safetensors","q":null,"stTotal":7.248},"moe":false,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29},"mem":{"bf16":{"w":14.5,"t":17.5},"fp8":{"w":7.7,"t":10},"q4":{"w":4.39,"t":6.4}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":28.99,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Mistral-7B-Instruct-v0.3","kind":"Instruct"},{"id":"mistralai/Mistral-7B-v0.3","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Mistral-7B-Instruct-v0.3","u":"https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-mistral-7b-instruct-v0-3"},{"id":"mistral-large-instruct-2411","name":"Mistral-Large-Instruct-2411","hf":"mistralai/Mistral-Large-Instruct-2411","org":"mistralai","family":"mistral","series":"Mistral-Large","task":"llm","pipeline":null,"tags":[],"released":"2024-11-14","updated":"2025-07-28","gated":false,"params":{"total":122.61,"active":null,"src":"safetensors","q":null,"stTotal":122.61},"moe":false,"ctx":131072,"arch":{"L":88,"attn":88,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.95,"32768":11.81,"131072":47.24},"mem":{"bf16":{"w":245.22,"t":273.2},"fp8":{"w":130.27,"t":146.8},"q4":{"w":74.33,"t":85.2}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":490.44,"native":"BF16","license":{"id":"mrl","name":"Mistral Research License","link":"https://mistral.ai/licenses/MRL-0.1.md","cls":"nc"},"runtimes":[{"id":"vllm","via":"card"}],"variants":[{"id":"mistralai/Mistral-Large-Instruct-2411","kind":"Instruct"}],"sources":[{"t":"Hugging Face · mistralai/Mistral-Large-Instruct-2411","u":"https://huggingface.co/mistralai/Mistral-Large-Instruct-2411"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mistral-Large-Instruct-2411/blob/main/config.json"},{"t":"License","u":"https://mistral.ai/licenses/MRL-0.1.md"}],"page":"https://aimap.page/en/models/compute/open-models/mistral-large-instruct-2411/"},{"id":"mistral-large-instruct-2407","name":"Mistral-Large-Instruct-2407","hf":"mistralai/Mistral-Large-Instruct-2407","org":"mistralai","family":"mistral","series":"Mistral-Large","task":"llm","pipeline":null,"tags":[],"released":"2024-07-24","updated":"2025-07-28","gated":true,"params":{"total":122.61,"active":null,"src":"safetensors","q":null,"stTotal":122.61},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":245.22,"t":270.2},"fp8":{"w":130.27,"t":143.8},"q4":{"w":74.33,"t":82.3}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":490.44,"native":"BF16","license":{"id":"mrl","name":"Mistral Research License","link":"https://mistral.ai/licenses/MRL-0.1.md","cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Mistral-Large-Instruct-2407","kind":"Instruct"}],"sources":[{"t":"Hugging Face · mistralai/Mistral-Large-Instruct-2407","u":"https://huggingface.co/mistralai/Mistral-Large-Instruct-2407"},{"t":"License","u":"https://mistral.ai/licenses/MRL-0.1.md"}],"page":"https://aimap.page/en/models/compute/open-models/mistral-large-instruct-2407/"},{"id":"mistral-large-3-675b-instruct-2512","name":"Mistral-Large-3-675B-Instruct-2512","hf":"mistralai/Mistral-Large-3-675B-Instruct-2512","org":"mistralai","family":"mistral","series":"Mistral-Large-3","task":"llm","pipeline":null,"tags":[],"released":"2025-11-28","updated":"2026-07-15","gated":false,"params":{"total":675,"active":41,"src":"card","q":"41B active parameters and 675B total parameters","stTotal":null},"moe":true,"ctx":294912,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":576,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.58,"32768":2.3,"131072":9.21},"mem":{"bf16":{"w":1350,"t":1486.1},"fp8":{"w":717.19,"t":790},"q4":{"w":409.22,"t":451.2}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":681.5,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Mistral-Large-3-675B-Instruct-2512-NVFP4","kind":"Instruct/NVFP4"},{"id":"mistralai/Mistral-Large-3-675B-Instruct-2512","kind":"Instruct"}],"sources":[{"t":"Hugging Face · mistralai/Mistral-Large-3-675B-Instruct-2512","u":"https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/mistral-large-3-675b-instruct-2512/"},{"id":"mistral-medium-3-5-128b","name":"Mistral-Medium-3.5-128B","hf":"mistralai/Mistral-Medium-3.5-128B","org":"mistralai","family":"mistral","series":"Mistral-Medium-3.5","task":"llm","pipeline":null,"tags":[],"released":"2026-03-31","updated":"2026-07-15","gated":false,"params":{"total":127.704,"active":null,"src":"safetensors","q":null,"stTotal":127.704},"moe":false,"ctx":262144,"arch":{"L":88,"attn":88,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.95,"32768":11.81,"131072":47.24},"mem":{"bf16":{"w":255.41,"t":284.4},"fp8":{"w":135.69,"t":152.7},"q4":{"w":77.42,"t":88.6}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"h200","mac":"mac256"}},"disk":267.21,"native":"F8_E4M3","license":{"id":"other","name":"other","link":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"mistral-medium-3.5:128b","url":"https://ollama.com/library/mistral-medium-3.5"}],"variants":[{"id":"mistralai/Mistral-Medium-3.5-128B","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Mistral-Medium-3.5-128B","u":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B/blob/main/LICENSE"},{"t":"Ollama library · mistral-medium-3.5","u":"https://ollama.com/library/mistral-medium-3.5"}],"page":"https://aimap.page/en/models/compute/open-models/mistral-medium-3-5-128b/"},{"id":"mistral-nemo-instruct-2407","name":"Mistral-Nemo-Instruct-2407","hf":"mistralai/Mistral-Nemo-Instruct-2407","org":"mistralai","family":"mistral","series":"Mistral-Nemo","task":"llm","pipeline":null,"tags":[],"released":"2024-07-17","updated":"2025-07-28","gated":false,"params":{"total":12.248,"active":null,"src":"safetensors","q":null,"stTotal":12.248},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":24.5,"t":28.8},"fp8":{"w":13.01,"t":16.2},"q4":{"w":7.43,"t":10}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac24"}},"disk":48.99,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Mistral-Nemo-Instruct-2407","kind":"Instruct"},{"id":"mistralai/Mistral-Nemo-Base-2407","kind":"Base"},{"id":"mistralai/Mistral-Nemo-Instruct-FP8-2407","kind":"Instruct/FP8"}],"sources":[{"t":"Hugging Face · mistralai/Mistral-Nemo-Instruct-2407","u":"https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-mistral-nemo-instruct-2407"},{"id":"mistral-small-instruct-2409","name":"Mistral-Small-Instruct-2409","hf":"mistralai/Mistral-Small-Instruct-2409","org":"mistralai","family":"mistral","series":"Mistral-Small","task":"llm","pipeline":null,"tags":[],"released":"2024-09-17","updated":"2025-07-28","gated":false,"params":{"total":22.247,"active":null,"src":"safetensors","q":null,"stTotal":22.247},"moe":false,"ctx":32768,"arch":{"L":56,"attn":56,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.88,"32768":7.52},"mem":{"bf16":{"w":44.49,"t":51.3},"fp8":{"w":23.64,"t":28.4},"q4":{"w":13.49,"t":17.2}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":88.99,"native":"BF16","license":{"id":"mrl","name":"Mistral Research License","link":"https://mistral.ai/licenses/MRL-0.1.md","cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Mistral-Small-Instruct-2409","kind":"Instruct"}],"sources":[{"t":"Hugging Face · mistralai/Mistral-Small-Instruct-2409","u":"https://huggingface.co/mistralai/Mistral-Small-Instruct-2409"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mistral-Small-Instruct-2409/blob/main/config.json"},{"t":"License","u":"https://mistral.ai/licenses/MRL-0.1.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-mistral-small-instruct-2409"},{"id":"mistral-small-24b-instruct-2501","name":"Mistral-Small-24B-Instruct-2501","hf":"mistralai/Mistral-Small-24B-Instruct-2501","org":"mistralai","family":"mistral","series":"Mistral-Small","task":"llm","pipeline":null,"tags":[],"released":"2025-01-28","updated":"2025-07-28","gated":false,"params":{"total":23.572,"active":null,"src":"safetensors","q":null,"stTotal":23.572},"moe":false,"ctx":32768,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37},"mem":{"bf16":{"w":47.14,"t":53.7},"fp8":{"w":25.05,"t":29.4},"q4":{"w":14.29,"t":17.6}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":94.29,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Mistral-Small-24B-Instruct-2501","kind":"Instruct"},{"id":"mistralai/Mistral-Small-24B-Base-2501","kind":"Base"}],"sources":[{"t":"Hugging Face · mistralai/Mistral-Small-24B-Instruct-2501","u":"https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-mistral-small-24b-instruct-2501"},{"id":"mistral-small-3-1-24b-instruct-2503","name":"Mistral-Small-3.1-24B-Instruct-2503","hf":"mistralai/Mistral-Small-3.1-24B-Instruct-2503","org":"mistralai","family":"mistral","series":"Mistral-Small-3.1","task":"llm","pipeline":null,"tags":[],"released":"2025-03-11","updated":"2025-12-22","gated":false,"params":{"total":24.011,"active":null,"src":"safetensors","q":null,"stTotal":24.011},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":48.02,"t":54.7},"fp8":{"w":25.51,"t":29.9},"q4":{"w":14.56,"t":17.9}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":96.05,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Mistral-Small-3.1-24B-Instruct-2503","kind":"Instruct"},{"id":"mistralai/Devstral-Small-2-24B-Instruct-2512","kind":"Instruct"},{"id":"mistralai/Mistral-Small-3.1-24B-Base-2503","kind":"Base"}],"sources":[{"t":"Hugging Face · mistralai/Mistral-Small-3.1-24B-Instruct-2503","u":"https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-mistral-small-3-1-24b-instruct-2503"},{"id":"mistral-small-3-2-24b-instruct-2506","name":"Mistral-Small-3.2-24B-Instruct-2506","hf":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","org":"mistralai","family":"mistral","series":"Mistral-Small-3.2","task":"llm","pipeline":null,"tags":[],"released":"2025-06-19","updated":"2025-12-22","gated":false,"params":{"total":24.011,"active":null,"src":"safetensors","q":null,"stTotal":24.011},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":48.02,"t":54.7},"fp8":{"w":25.51,"t":29.9},"q4":{"w":14.56,"t":17.9}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":96.05,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","kind":"Instruct"}],"sources":[{"t":"Hugging Face · mistralai/Mistral-Small-3.2-24B-Instruct-2506","u":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-mistral-small-3-2-24b-instruct-2506"},{"id":"mistral-small-4-119b-2603","name":"Mistral-Small-4-119B-2603","hf":"mistralai/Mistral-Small-4-119B-2603","org":"mistralai","family":"mistral","series":"Mistral-Small-4","task":"llm","pipeline":null,"tags":[],"released":"2026-01-23","updated":"2026-07-15","gated":false,"params":{"total":119,"active":6.5,"src":"card","q":"119B parameters, with 6.5B activated per token","stTotal":119.401},"moe":true,"ctx":1048576,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":320,"kvMethod":"mla","exotic":[]},"kv":{"8192":0.19,"32768":0.75,"131072":3.02},"mem":{"bf16":{"w":238,"t":262.5},"fp8":{"w":126.44,"t":139.8},"q4":{"w":72.14,"t":80}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":241.85,"native":"F8_E4M3","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Mistral-Small-4-119B-2603","kind":"main"},{"id":"mistralai/Mistral-Small-4-119B-2603-NVFP4","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · mistralai/Mistral-Small-4-119B-2603","u":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/mistral-small-4-119b-2603/"},{"id":"mixtral-8x7b-instruct-v0-1","name":"Mixtral-8x7B-Instruct-v0.1","hf":"mistralai/Mixtral-8x7B-Instruct-v0.1","org":"mistralai","family":"mistral","series":"Mixtral","task":"llm","pipeline":null,"tags":[],"released":"2023-12-10","updated":"2025-07-24","gated":false,"params":{"total":46.703,"active":null,"src":"safetensors","q":null,"stTotal":46.703},"moe":true,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29},"mem":{"bf16":{"w":93.41,"t":104.3},"fp8":{"w":49.62,"t":56.2},"q4":{"w":28.31,"t":32.7}},"fits":{"bf16":{"gpu":"h200","mac":"mac256"},"fp8":{"gpu":"2x5090","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac64"}},"disk":93.41,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Mixtral-8x7B-Instruct-v0.1","kind":"Instruct"}],"sources":[{"t":"Hugging Face · mistralai/Mixtral-8x7B-Instruct-v0.1","u":"https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-mixtral-8x7b-instruct-v0-1"},{"id":"mixtral-8x22b-instruct-v0-1","name":"Mixtral-8x22B-Instruct-v0.1","hf":"mistralai/Mixtral-8x22B-Instruct-v0.1","org":"mistralai","family":"mistral","series":"Mixtral","task":"llm","pipeline":null,"tags":[],"released":"2024-04-16","updated":"2025-07-24","gated":false,"params":{"total":140.63,"active":null,"src":"safetensors","q":null,"stTotal":140.63},"moe":true,"ctx":65536,"arch":{"L":56,"attn":56,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.88,"32768":7.52},"mem":{"bf16":{"w":281.26,"t":311.8},"fp8":{"w":149.42,"t":166.7},"q4":{"w":85.26,"t":96.2}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"h200","mac":"mac256"}},"disk":281.26,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Mixtral-8x22B-Instruct-v0.1","kind":"Instruct"}],"sources":[{"t":"Hugging Face · mistralai/Mixtral-8x22B-Instruct-v0.1","u":"https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1"},{"t":"config.json","u":"https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/mixtral-8x22b-instruct-v0-1/"},{"id":"pixtral-12b-2409","name":"Pixtral-12B-2409","hf":"mistralai/Pixtral-12B-2409","org":"mistralai","family":"mistral","series":"Pixtral","task":"llm","pipeline":null,"tags":[],"released":"2024-09-11","updated":"2026-06-02","gated":false,"params":{"total":12,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":24,"t":28.2},"fp8":{"w":12.75,"t":15.9},"q4":{"w":7.27,"t":9.8}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac24"}},"disk":25.37,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"}],"variants":[{"id":"mistralai/Pixtral-12B-2409","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Pixtral-12B-2409","u":"https://huggingface.co/mistralai/Pixtral-12B-2409"},{"t":"config.json","u":"https://huggingface.co/mistralai/Pixtral-12B-2409/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-pixtral-12b-2409"},{"id":"shieldstral-1-0-3b","name":"Shieldstral-1.0-3B","hf":"mistralai/Shieldstral-1.0-3B","org":"mistralai","family":"mistral","series":"Shieldstral-1.0","task":"guard","pipeline":null,"tags":[],"released":"2026-07-16","updated":"2026-08-05","gated":false,"params":{"total":3.849,"active":null,"src":"safetensors","q":null,"stTotal":3.849},"moe":false,"ctx":262144,"arch":{"L":26,"attn":26,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.87,"32768":3.49,"131072":13.96},"mem":{"bf16":{"w":7.7,"t":9.8},"fp8":{"w":4.09,"t":5.9},"q4":{"w":2.33,"t":3.9}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.4,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Shieldstral-1.0-3B","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Shieldstral-1.0-3B","u":"https://huggingface.co/mistralai/Shieldstral-1.0-3B"},{"t":"config.json","u":"https://huggingface.co/mistralai/Shieldstral-1.0-3B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-shieldstral-1-0-3b"},{"id":"voxtral-mini-3b-2507","name":"Voxtral-Mini-3B-2507","hf":"mistralai/Voxtral-Mini-3B-2507","org":"mistralai","family":"mistral","series":"Voxtral-Mini","task":"llm","pipeline":null,"tags":[],"released":"2025-07-01","updated":"2025-07-28","gated":false,"params":{"total":4.676,"active":null,"src":"safetensors","q":null,"stTotal":4.676},"moe":false,"ctx":131072,"arch":{"L":30,"attn":30,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.01,"32768":4.03,"131072":16.11},"mem":{"bf16":{"w":9.35,"t":11.8},"fp8":{"w":4.97,"t":7},"q4":{"w":2.83,"t":4.6}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":18.71,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Voxtral-Mini-3B-2507","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Voxtral-Mini-3B-2507","u":"https://huggingface.co/mistralai/Voxtral-Mini-3B-2507"},{"t":"config.json","u":"https://huggingface.co/mistralai/Voxtral-Mini-3B-2507/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-voxtral-mini-3b-2507"},{"id":"voxtral-mini-4b-realtime-2602","name":"Voxtral-Mini-4B-Realtime-2602","hf":"mistralai/Voxtral-Mini-4B-Realtime-2602","org":"mistralai","family":"mistral","series":"Voxtral-Mini-Realtime","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-01-21","updated":"2026-03-11","gated":false,"params":{"total":4.43,"active":null,"src":"safetensors","q":null,"stTotal":4.43},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":8.86,"t":10.2},"fp8":{"w":4.71,"t":5.7},"q4":{"w":2.69,"t":3.5}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.72,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Voxtral-Mini-4B-Realtime-2602","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Voxtral-Mini-4B-Realtime-2602","u":"https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602"},{"t":"config.json","u":"https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-voxtral-mini-4b-realtime-2602"},{"id":"voxtral-mini-4b-realtime-arabic","name":"Voxtral-Mini-4B-Realtime-Arabic","hf":"mistralai/Voxtral-Mini-4B-Realtime-Arabic","org":"mistralai","family":"mistral","series":"Voxtral-Mini-Realtime-Arabic","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-10-08","updated":"2026-10-12","gated":false,"params":{"total":4.43,"active":null,"src":"safetensors","q":null,"stTotal":4.43},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":8.86,"t":10.2},"fp8":{"w":4.71,"t":5.7},"q4":{"w":2.69,"t":3.5}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.72,"native":"BF16","license":{"id":null,"name":null,"link":null,"cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Voxtral-Mini-4B-Realtime-Arabic","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Voxtral-Mini-4B-Realtime-Arabic","u":"https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-Arabic"},{"t":"config.json","u":"https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-Arabic/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/voxtral-mini-4b-realtime-arabic/"},{"id":"voxtral-small-24b-2507","name":"Voxtral-Small-24B-2507","hf":"mistralai/Voxtral-Small-24B-2507","org":"mistralai","family":"mistral","series":"Voxtral-Small","task":"omni","pipeline":"audio-text-to-text","tags":[],"released":"2025-07-01","updated":"2025-12-20","gated":false,"params":{"total":24.262,"active":null,"src":"safetensors","q":null,"stTotal":24.262},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":48.52,"t":55.2},"fp8":{"w":25.78,"t":30.2},"q4":{"w":14.71,"t":18}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":97.05,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"mistralai/Voxtral-Small-24B-2507","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Voxtral-Small-24B-2507","u":"https://huggingface.co/mistralai/Voxtral-Small-24B-2507"},{"t":"config.json","u":"https://huggingface.co/mistralai/Voxtral-Small-24B-2507/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-voxtral-small-24b-2507"},{"id":"voxtral-4b-tts-2603","name":"Voxtral-4B-TTS-2603","hf":"mistralai/Voxtral-4B-TTS-2603","org":"mistralai","family":"mistral","series":"Voxtral-TTS","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2025-11-17","updated":"2026-03-31","gated":false,"params":{"total":4,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":128000,"arch":null,"kv":null,"mem":{"bf16":{"w":8,"t":9.3},"fp8":{"w":4.25,"t":5.2},"q4":{"w":2.42,"t":3.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8,"native":null,"license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"vllm","via":"card"}],"variants":[{"id":"mistralai/Voxtral-4B-TTS-2603","kind":"main"}],"sources":[{"t":"Hugging Face · mistralai/Voxtral-4B-TTS-2603","u":"https://huggingface.co/mistralai/Voxtral-4B-TTS-2603"},{"t":"config.json","u":"https://huggingface.co/mistralai/Voxtral-4B-TTS-2603/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/mistral/#m-voxtral-4b-tts-2603"},{"id":"fara-7b","name":"Fara-7B","hf":"microsoft/Fara-7B","org":"microsoft","family":"ms-other","series":"Fara","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-10-30","updated":"2026-08-12","gated":false,"params":{"total":8.292,"active":null,"src":"safetensors","q":null,"stTotal":8.292},"moe":false,"ctx":128000,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":16.58,"t":19.2},"fp8":{"w":8.81,"t":10.7},"q4":{"w":5.03,"t":6.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.58,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Fara-7B","kind":"main"},{"id":"microsoft/Fara-7B-onnx","kind":"ONNX"}],"sources":[{"t":"Hugging Face · microsoft/Fara-7B","u":"https://huggingface.co/microsoft/Fara-7B"},{"t":"config.json","u":"https://huggingface.co/microsoft/Fara-7B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ms-other/#m-fara-7b"},{"id":"fara1-5-4b","name":"Fara1.5-4B","hf":"microsoft/Fara1.5-4B","org":"microsoft","family":"ms-other","series":"Fara1.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-07-17","updated":"2026-07-27","gated":false,"params":{"total":4.539,"active":null,"src":"safetensors","q":null,"stTotal":4.539},"moe":false,"ctx":262144,"arch":{"L":32,"attn":8,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.27,"32768":1.07,"131072":4.29},"mem":{"bf16":{"w":9.08,"t":10.8},"fp8":{"w":4.82,"t":6.1},"q4":{"w":2.75,"t":3.8}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":9.08,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Fara1.5-4B","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/Fara1.5-4B","u":"https://huggingface.co/microsoft/Fara1.5-4B"},{"t":"config.json","u":"https://huggingface.co/microsoft/Fara1.5-4B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ms-other/#m-fara1-5-4b"},{"id":"fara1-5-9b","name":"Fara1.5-9B","hf":"microsoft/Fara1.5-9B","org":"microsoft","family":"ms-other","series":"Fara1.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-05-12","updated":"2026-07-27","gated":false,"params":{"total":9.41,"active":null,"src":"safetensors","q":null,"stTotal":9.41},"moe":false,"ctx":262144,"arch":{"L":32,"attn":8,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.27,"32768":1.07,"131072":4.29},"mem":{"bf16":{"w":18.82,"t":21.5},"fp8":{"w":10,"t":11.8},"q4":{"w":5.7,"t":7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":18.82,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Fara1.5-9B","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/Fara1.5-9B","u":"https://huggingface.co/microsoft/Fara1.5-9B"},{"t":"config.json","u":"https://huggingface.co/microsoft/Fara1.5-9B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ms-other/#m-fara1-5-9b"},{"id":"fara1-5-27b","name":"Fara1.5-27B","hf":"microsoft/Fara1.5-27B","org":"microsoft","family":"ms-other","series":"Fara1.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-07-17","updated":"2026-07-27","gated":false,"params":{"total":27.357,"active":null,"src":"safetensors","q":null,"stTotal":27.357},"moe":false,"ctx":262144,"arch":{"L":64,"attn":16,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.54,"32768":2.15,"131072":8.59},"mem":{"bf16":{"w":54.71,"t":61.2},"fp8":{"w":29.07,"t":33},"q4":{"w":16.59,"t":19.3}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":54.71,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Fara1.5-27B","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/Fara1.5-27B","u":"https://huggingface.co/microsoft/Fara1.5-27B"},{"t":"config.json","u":"https://huggingface.co/microsoft/Fara1.5-27B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ms-other/#m-fara1-5-27b"},{"id":"vibevoice-1-5b","name":"VibeVoice-1.5B","hf":"microsoft/VibeVoice-1.5B","org":"microsoft","family":"ms-other","series":"VibeVoice","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2025-08-25","updated":"2026-01-22","gated":false,"params":{"total":2.704,"active":null,"src":"safetensors","q":null,"stTotal":2.704},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":5.41,"t":6.4},"fp8":{"w":2.87,"t":3.7},"q4":{"w":1.64,"t":2.3}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.41,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/VibeVoice-1.5B","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/VibeVoice-1.5B","u":"https://huggingface.co/microsoft/VibeVoice-1.5B"},{"t":"config.json","u":"https://huggingface.co/microsoft/VibeVoice-1.5B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ms-other/#m-vibevoice-1-5b"},{"id":"vibevoice-asr","name":"VibeVoice-ASR","hf":"microsoft/VibeVoice-ASR","org":"microsoft","family":"ms-other","series":"VibeVoice-ASR","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-01-21","updated":"2026-01-27","gated":false,"params":{"total":8.674,"active":null,"src":"safetensors","q":null,"stTotal":8.674},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":17.35,"t":19.6},"fp8":{"w":9.22,"t":10.6},"q4":{"w":5.26,"t":6.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.35,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/VibeVoice-ASR","kind":"main"},{"id":"microsoft/VibeVoice-ASR-HF","kind":"HF-transformers"}],"sources":[{"t":"Hugging Face · microsoft/VibeVoice-ASR","u":"https://huggingface.co/microsoft/VibeVoice-ASR"},{"t":"config.json","u":"https://huggingface.co/microsoft/VibeVoice-ASR/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ms-other/#m-vibevoice-asr"},{"id":"vibevoice-asr-streaming-1-5b","name":"VibeVoice-ASR-Streaming-1.5B","hf":"microsoft/VibeVoice-ASR-Streaming-1.5B","org":"microsoft","family":"ms-other","series":"VibeVoice-ASR-Streaming","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-09-02","updated":"2026-09-03","gated":false,"params":{"total":2.814,"active":null,"src":"safetensors","q":null,"stTotal":2.814},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":5.63,"t":6.7},"fp8":{"w":2.99,"t":3.8},"q4":{"w":1.71,"t":2.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.63,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/VibeVoice-ASR-Streaming-1.5B","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/VibeVoice-ASR-Streaming-1.5B","u":"https://huggingface.co/microsoft/VibeVoice-ASR-Streaming-1.5B"},{"t":"config.json","u":"https://huggingface.co/microsoft/VibeVoice-ASR-Streaming-1.5B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/vibevoice-asr-streaming-1-5b/"},{"id":"vibevoice-asr-streaming-7b","name":"VibeVoice-ASR-Streaming-7B","hf":"microsoft/VibeVoice-ASR-Streaming-7B","org":"microsoft","family":"ms-other","series":"VibeVoice-ASR-Streaming","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-09-02","updated":"2026-09-03","gated":false,"params":{"total":8.674,"active":null,"src":"safetensors","q":null,"stTotal":8.674},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":17.35,"t":19.6},"fp8":{"w":9.22,"t":10.6},"q4":{"w":5.26,"t":6.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.35,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/VibeVoice-ASR-Streaming-7B","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/VibeVoice-ASR-Streaming-7B","u":"https://huggingface.co/microsoft/VibeVoice-ASR-Streaming-7B"},{"t":"config.json","u":"https://huggingface.co/microsoft/VibeVoice-ASR-Streaming-7B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/vibevoice-asr-streaming-7b/"},{"id":"vibevoice-realtime-0-5b","name":"VibeVoice-Realtime-0.5B","hf":"microsoft/VibeVoice-Realtime-0.5B","org":"microsoft","family":"ms-other","series":"VibeVoice-Realtime","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2025-12-04","updated":"2025-12-12","gated":false,"params":{"total":1.018,"active":null,"src":"safetensors","q":null,"stTotal":1.018},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":2.04,"t":2.7},"fp8":{"w":1.08,"t":1.7},"q4":{"w":0.62,"t":1.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.04,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/VibeVoice-Realtime-0.5B","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/VibeVoice-Realtime-0.5B","u":"https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B"},{"t":"config.json","u":"https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ms-other/#m-vibevoice-realtime-0-5b"},{"id":"harrier-oss-v1-270m","name":"harrier-oss-v1-270m","hf":"microsoft/harrier-oss-v1-270m","org":"microsoft","family":"ms-other","series":"harrier-oss","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-03-30","updated":"2026-03-30","gated":false,"params":{"total":0.268,"active":null,"src":"safetensors","q":null,"stTotal":0.268},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":0.54,"t":1.1},"fp8":{"w":0.28,"t":0.8},"q4":{"w":0.16,"t":0.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.54,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"microsoft/harrier-oss-v1-270m","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/harrier-oss-v1-270m","u":"https://huggingface.co/microsoft/harrier-oss-v1-270m"},{"t":"config.json","u":"https://huggingface.co/microsoft/harrier-oss-v1-270m/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ms-other/#m-harrier-oss-v1-270m"},{"id":"harrier-oss-v1-0-6b","name":"harrier-oss-v1-0.6b","hf":"microsoft/harrier-oss-v1-0.6b","org":"microsoft","family":"ms-other","series":"harrier-oss","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-03-30","updated":"2026-03-30","gated":false,"params":{"total":0.596,"active":null,"src":"safetensors","q":null,"stTotal":0.596},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":1.19,"t":1.8},"fp8":{"w":0.63,"t":1.2},"q4":{"w":0.36,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.19,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"microsoft/harrier-oss-v1-0.6b","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/harrier-oss-v1-0.6b","u":"https://huggingface.co/microsoft/harrier-oss-v1-0.6b"},{"t":"config.json","u":"https://huggingface.co/microsoft/harrier-oss-v1-0.6b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ms-other/#m-harrier-oss-v1-0-6b"},{"id":"harrier-oss-v1-27b","name":"harrier-oss-v1-27b","hf":"microsoft/harrier-oss-v1-27b","org":"microsoft","family":"ms-other","series":"harrier-oss","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2026-03-30","updated":"2026-03-30","gated":false,"params":{"total":27.009,"active":null,"src":"safetensors","q":null,"stTotal":27.009},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":54.02,"t":59.9},"fp8":{"w":28.7,"t":32.1},"q4":{"w":16.37,"t":18.5}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":54.02,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"microsoft/harrier-oss-v1-27b","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/harrier-oss-v1-27b","u":"https://huggingface.co/microsoft/harrier-oss-v1-27b"},{"t":"config.json","u":"https://huggingface.co/microsoft/harrier-oss-v1-27b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/ms-other/#m-harrier-oss-v1-27b"},{"id":"llama-3-1-nemotron-70b-instruct-hf","name":"Llama-3.1-Nemotron-70B-Instruct-HF","hf":"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","org":"nvidia","family":"nemotron","series":"Llama-3.1-Nemotron","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-10-12","updated":"2025-04-13","gated":false,"params":{"total":70.554,"active":null,"src":"safetensors","q":null,"stTotal":70.554},"moe":false,"ctx":131072,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74,"131072":42.95},"mem":{"bf16":{"w":141.11,"t":158.4},"fp8":{"w":74.96,"t":85.6},"q4":{"w":42.77,"t":50.2}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"pro6000","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":141.11,"native":"BF16","license":{"id":"llama3.1","name":"Llama 3.1 Community","link":null,"cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","kind":"Instruct/HF-transformers"}],"sources":[{"t":"Hugging Face · nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","u":"https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF"},{"t":"config.json","u":"https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-3-1-nemotron-70b-instruct-hf"},{"id":"llama-3-1-nemotron-nano-4b-v1-1","name":"Llama-3.1-Nemotron-Nano-4B-v1.1","hf":"nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1","org":"nvidia","family":"nemotron","series":"Llama-3.1-Nemotron-Nano","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-05-03","updated":"2025-10-15","gated":false,"params":{"total":4.513,"active":null,"src":"safetensors","q":null,"stTotal":4.513},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":9.03,"t":11.5},"fp8":{"w":4.8,"t":6.8},"q4":{"w":2.74,"t":4.6}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":9.03,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1","u":"https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1"},{"t":"config.json","u":"https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-3-1-nemotron-nano-4b-v1-1"},{"id":"llama-3-1-nemotron-nano-8b-v1","name":"Llama-3.1-Nemotron-Nano-8B-v1","hf":"nvidia/Llama-3.1-Nemotron-Nano-8B-v1","org":"nvidia","family":"nemotron","series":"Llama-3.1-Nemotron-Nano","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-03-16","updated":"2025-10-15","gated":false,"params":{"total":8.03,"active":null,"src":"safetensors","q":null,"stTotal":8.03},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":16.06,"t":19.2},"fp8":{"w":8.53,"t":11},"q4":{"w":4.87,"t":6.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.06,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Llama-3.1-Nemotron-Nano-8B-v1","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Llama-3.1-Nemotron-Nano-8B-v1","u":"https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-8B-v1"},{"t":"config.json","u":"https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-8B-v1/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-3-1-nemotron-nano-8b-v1"},{"id":"llama-3-1-nemotron-nano-vl-8b-v1","name":"Llama-3.1-Nemotron-Nano-VL-8B-V1","hf":"nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1","org":"nvidia","family":"nemotron","series":"Llama-3.1-Nemotron-Nano-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-06-03","updated":"2025-12-04","gated":false,"params":{"total":8.722,"active":null,"src":"safetensors","q":null,"stTotal":8.722},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":17.44,"t":20.8},"fp8":{"w":9.27,"t":11.8},"q4":{"w":5.29,"t":7.4}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":17.44,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1","u":"https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1"},{"t":"config.json","u":"https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-3-1-nemotron-nano-vl-8b-v1"},{"id":"llama-3-1-nemotron-8b-ultralong-1m-instruct","name":"Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct","hf":"nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct","org":"nvidia","family":"nemotron","series":"Llama-3.1-Nemotron-UltraLong","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-03-04","updated":"2025-04-17","gated":false,"params":{"total":8.037,"active":null,"src":"safetensors","q":null,"stTotal":8.037},"moe":false,"ctx":1073152,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":16.07,"t":19.3},"fp8":{"w":8.54,"t":11},"q4":{"w":4.87,"t":6.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":32.15,"native":"F32","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct","u":"https://huggingface.co/nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct"},{"t":"config.json","u":"https://huggingface.co/nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-3-1-nemotron-8b-ultralong-1m-instruct"},{"id":"llama-3-1-nemotron-51b-instruct","name":"Llama-3_1-Nemotron-51B-Instruct","hf":"nvidia/Llama-3_1-Nemotron-51B-Instruct","org":"nvidia","family":"nemotron","series":"Llama-3_1-Nemotron","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-22","updated":"2025-07-06","gated":false,"params":{"total":51.501,"active":null,"src":"safetensors","q":null,"stTotal":51.501},"moe":false,"ctx":131072,"arch":{"L":80,"attn":54,"slide":0,"win":null,"kvElems":1758.8,"kvMethod":"gqa-nas","exotic":[]},"kv":{"8192":1.56,"32768":6.22,"131072":24.9},"mem":{"bf16":{"w":103,"t":115.4},"fp8":{"w":54.72,"t":62.3},"q4":{"w":31.22,"t":36.4}},"fits":{"bf16":{"gpu":"h200","mac":"mac256"},"fp8":{"gpu":"h100","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac64"}},"disk":103,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Llama-3_1-Nemotron-51B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · nvidia/Llama-3_1-Nemotron-51B-Instruct","u":"https://huggingface.co/nvidia/Llama-3_1-Nemotron-51B-Instruct"},{"t":"config.json","u":"https://huggingface.co/nvidia/Llama-3_1-Nemotron-51B-Instruct/blob/main/config.json"},{"t":"License","u":"https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-3-1-nemotron-51b-instruct"},{"id":"llama-3-1-nemotron-ultra-253b-v1","name":"Llama-3_1-Nemotron-Ultra-253B-v1","hf":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","org":"nvidia","family":"nemotron","series":"Llama-3_1-Nemotron-Ultra","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-07","updated":"2025-10-15","gated":false,"params":{"total":253.401,"active":null,"src":"safetensors","q":null,"stTotal":253.401},"moe":false,"ctx":131072,"arch":{"L":162,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa-nas","exotic":[]},"kv":{"8192":2.15,"32768":8.59,"131072":34.36},"mem":{"bf16":{"w":506.8,"t":560.1},"fp8":{"w":269.24,"t":298.8},"q4":{"w":153.62,"t":171.6}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":506.8,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","kind":"main"},{"id":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","u":"https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1"},{"t":"config.json","u":"https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/llama-3-1-nemotron-ultra-253b-v1/"},{"id":"llama-3-3-nemotron-super-49b-v1","name":"Llama-3_3-Nemotron-Super-49B-v1","hf":"nvidia/Llama-3_3-Nemotron-Super-49B-v1","org":"nvidia","family":"nemotron","series":"Llama-3_3-Nemotron-Super","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-03-16","updated":"2025-10-15","gated":false,"params":{"total":49.867,"active":null,"src":"safetensors","q":null,"stTotal":49.867},"moe":false,"ctx":131072,"arch":{"L":80,"attn":49,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa-nas","exotic":[]},"kv":{"8192":1.64,"32768":6.58,"131072":26.31},"mem":{"bf16":{"w":99.73,"t":111.8},"fp8":{"w":52.98,"t":60.4},"q4":{"w":30.23,"t":35.4}},"fits":{"bf16":{"gpu":"h200","mac":"mac256"},"fp8":{"gpu":"h100","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac64"}},"disk":99.73,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Llama-3_3-Nemotron-Super-49B-v1","kind":"main"},{"id":"nvidia/Llama-3_3-Nemotron-Super-49B-v1-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · nvidia/Llama-3_3-Nemotron-Super-49B-v1","u":"https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1"},{"t":"config.json","u":"https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-3-3-nemotron-super-49b-v1"},{"id":"llama-3-3-nemotron-super-49b-v1-5","name":"Llama-3_3-Nemotron-Super-49B-v1_5","hf":"nvidia/Llama-3_3-Nemotron-Super-49B-v1_5","org":"nvidia","family":"nemotron","series":"Llama-3_3-Nemotron-Super_5","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-25","updated":"2025-10-15","gated":false,"params":{"total":49.867,"active":null,"src":"safetensors","q":null,"stTotal":49.867},"moe":false,"ctx":131072,"arch":{"L":80,"attn":49,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa-nas","exotic":[]},"kv":{"8192":1.64,"32768":6.58,"131072":26.31},"mem":{"bf16":{"w":99.73,"t":111.8},"fp8":{"w":52.98,"t":60.4},"q4":{"w":30.23,"t":35.4}},"fits":{"bf16":{"gpu":"h200","mac":"mac256"},"fp8":{"gpu":"h100","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac64"}},"disk":99.73,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Llama-3_3-Nemotron-Super-49B-v1_5","kind":"main"},{"id":"nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8","kind":"FP8"},{"id":"nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · nvidia/Llama-3_3-Nemotron-Super-49B-v1_5","u":"https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5"},{"t":"config.json","u":"https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-3-3-nemotron-super-49b-v1-5"},{"id":"nvidia-nemotron-3-nano-4b-bf16","name":"NVIDIA-Nemotron-3-Nano-4B-BF16","hf":"nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-3-Nano","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-03-07","updated":"2026-03-20","gated":false,"params":{"total":3.974,"active":null,"src":"safetensors","q":null,"stTotal":3.974},"moe":false,"ctx":262144,"arch":{"L":42,"attn":4,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.13,"32768":0.54,"131072":2.15},"mem":{"bf16":{"w":7.95,"t":9.4},"fp8":{"w":4.22,"t":5.3},"q4":{"w":2.41,"t":3.3}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.95,"native":"BF16","license":{"id":"nvidia-nemotron-open-model-license","name":"nvidia-nemotron-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16","kind":"BF16"},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-4B-GGUF","kind":"GGUF"},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-4B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nvidia-nemotron-3-nano-4b-bf16"},{"id":"nvidia-nemotron-3-nano-30b-a3b-bf16","name":"NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","hf":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-3-Nano","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-12-04","updated":"2026-08-24","gated":false,"params":{"total":31.578,"active":3,"src":"safetensors","q":null,"stTotal":31.578},"moe":true,"ctx":262144,"arch":{"L":52,"attn":6,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.05,"32768":0.2,"131072":0.81},"mem":{"bf16":{"w":63.16,"t":70},"fp8":{"w":33.55,"t":37.5},"q4":{"w":19.14,"t":21.6}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":63.16,"native":"BF16","license":{"id":"nvidia-nemotron-open-model-license","name":"nvidia-nemotron-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4","kind":"NVFP4"},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","kind":"BF16"},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","kind":"FP8"},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16","kind":"Base/BF16"},{"id":"nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-NVFP4","kind":"NVFP4"},{"id":"nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nvidia-nemotron-3-nano-30b-a3b-bf16"},{"id":"nvidia-nemotron-3-super-120b-a12b-bf16","name":"NVIDIA-Nemotron-3-Super-120B-A12B-BF16","hf":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-3-Super","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-03-10","updated":"2026-08-25","gated":false,"params":{"total":123.611,"active":12,"src":"safetensors","q":null,"stTotal":123.611},"moe":true,"ctx":262144,"arch":{"L":88,"attn":8,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.07,"32768":0.27,"131072":1.07},"mem":{"bf16":{"w":247.22,"t":272.5},"fp8":{"w":131.34,"t":145},"q4":{"w":74.94,"t":83}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":247.23,"native":"BF16","license":{"id":"nvidia-nemotron-open-model-license","name":"nvidia-nemotron-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","kind":"BF16"},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","kind":"NVFP4"},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","kind":"FP8"},{"id":"nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4","kind":"NVFP4"},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16","kind":"Base/BF16"},{"id":"nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/nvidia-nemotron-3-super-120b-a12b-bf16/"},{"id":"nvidia-nemotron-3-ultra-550b-a55b-bf16","name":"NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","hf":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-3-Ultra","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-06-03","updated":"2026-08-24","gated":false,"params":{"total":560.525,"active":55,"src":"safetensors","q":null,"stTotal":560.525},"moe":true,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":1121.05,"t":1233.7},"fp8":{"w":595.56,"t":655.6},"q4":{"w":339.82,"t":374.3}},"fits":{"bf16":{"gpu":"8xb200","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1121.06,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","kind":"BF16"},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","kind":"NVFP4"},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16","kind":"Base/BF16"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/nvidia-nemotron-3-ultra-550b-a55b-bf16/"},{"id":"nvidia-nemotron-3-5-bolt-74b-a9b-bf16","name":"NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16","hf":"nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-3.5-Bolt","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-10-09","updated":"2026-10-19","gated":false,"params":{"total":74.885,"active":9,"src":"safetensors","q":null,"stTotal":74.885},"moe":true,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":149.77,"t":165.2},"fp8":{"w":79.57,"t":88},"q4":{"w":45.4,"t":50.4}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":149.77,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF","kind":"GGUF"},{"id":"nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB","kind":"main"},{"id":"nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16","kind":"BF16"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/nvidia-nemotron-3-5-bolt-74b-a9b-bf16/"},{"id":"nvidia-nemotron-3-5-lightning-30b-a3b-bf16","name":"NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","hf":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-3.5-Lightning","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-08-01","updated":"2026-08-24","gated":false,"params":{"total":31.578,"active":3,"src":"safetensors","q":null,"stTotal":31.578},"moe":true,"ctx":262144,"arch":{"L":52,"attn":6,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.05,"32768":0.2,"131072":0.81},"mem":{"bf16":{"w":63.16,"t":70},"fp8":{"w":33.55,"t":37.5},"q4":{"w":19.14,"t":21.6}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":65.83,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4","kind":"NVFP4"},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","kind":"BF16"},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark","kind":"NVFP4"},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16","kind":"Base/BF16"},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nvidia-nemotron-3-5-lightning-30b-a3b-bf16"},{"id":"nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","name":"NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","hf":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-3.5-Super-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-10-12","updated":"2026-10-16","gated":false,"params":{"total":124.453,"active":12,"src":"safetensors","q":null,"stTotal":124.453},"moe":true,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":248.91,"t":274.3},"fp8":{"w":132.23,"t":146},"q4":{"w":75.45,"t":83.5}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":248.91,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","kind":"BF16"},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4","kind":"NVFP4"},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-LiLiCorr","kind":"NVFP4"},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16","kind":"Base/BF16"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/nvidia-nemotron-3-5-super-vl-120b-a12b-bf16/"},{"id":"nvidia-nemotron-labs-dory1-0-4b-bf16","name":"NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16","hf":"nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-Labs-Dory1.0","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-10-16","updated":"2026-10-16","gated":false,"params":{"total":3.975,"active":null,"src":"safetensors","q":null,"stTotal":3.975},"moe":false,"ctx":262144,"arch":{"L":72,"attn":9,"slide":27,"win":1024,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.42,"32768":1.32,"131072":4.95},"mem":{"bf16":{"w":7.95,"t":9.7},"fp8":{"w":4.22,"t":5.6},"q4":{"w":2.41,"t":3.6}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.95,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-GGUF","kind":"GGUF"},{"id":"nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16","kind":"BF16"},{"id":"nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4","kind":"NVFP4"},{"id":"nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/nvidia-nemotron-labs-dory1-0-4b-bf16/"},{"id":"nvidia-nemotron-nano-9b-v2","name":"NVIDIA-Nemotron-Nano-9B-v2","hf":"nvidia/NVIDIA-Nemotron-Nano-9B-v2","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-Nano","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-08-12","updated":"2026-03-05","gated":false,"params":{"total":8.888,"active":null,"src":"safetensors","q":null,"stTotal":8.888},"moe":false,"ctx":131072,"arch":{"L":56,"attn":4,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.13,"32768":0.54,"131072":2.15},"mem":{"bf16":{"w":17.78,"t":20.2},"fp8":{"w":9.44,"t":11},"q4":{"w":5.39,"t":6.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.78,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-Nano-9B-v2","kind":"main"},{"id":"nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8","kind":"FP8"},{"id":"nvidia/NVIDIA-Nemotron-Nano-9B-v2-NVFP4","kind":"NVFP4"},{"id":"nvidia/NVIDIA-Nemotron-Nano-9B-v2-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-Nano-9B-v2","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nvidia-nemotron-nano-9b-v2"},{"id":"nvidia-nemotron-nano-12b-v2","name":"NVIDIA-Nemotron-Nano-12B-v2","hf":"nvidia/NVIDIA-Nemotron-Nano-12B-v2","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-Nano","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-08-21","updated":"2025-11-25","gated":false,"params":{"total":12.31,"active":null,"src":"safetensors","q":null,"stTotal":12.31},"moe":false,"ctx":131072,"arch":{"L":62,"attn":6,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.2,"32768":0.81,"131072":3.22},"mem":{"bf16":{"w":24.62,"t":27.8},"fp8":{"w":13.08,"t":15.1},"q4":{"w":7.46,"t":8.9}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":24.62,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-Nano-12B-v2","kind":"main"},{"id":"nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-Nano-12B-v2","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nvidia-nemotron-nano-12b-v2"},{"id":"nvidia-nemotron-nano-9b-v2-japanese","name":"NVIDIA-Nemotron-Nano-9B-v2-Japanese","hf":"nvidia/NVIDIA-Nemotron-Nano-9B-v2-Japanese","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-Nano-Japanese","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-02-04","updated":"2026-04-21","gated":false,"params":{"total":8.888,"active":null,"src":"safetensors","q":null,"stTotal":8.888},"moe":false,"ctx":131072,"arch":{"L":56,"attn":4,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.13,"32768":0.54,"131072":2.15},"mem":{"bf16":{"w":17.78,"t":20.2},"fp8":{"w":9.44,"t":11},"q4":{"w":5.39,"t":6.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.78,"native":"BF16","license":{"id":"nvidia-nemotron-open-model-license","name":"nvidia-nemotron-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-Nano-9B-v2-Japanese","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-Nano-9B-v2-Japanese","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2-Japanese"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2-Japanese/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nvidia-nemotron-nano-9b-v2-japanese"},{"id":"nvidia-nemotron-nano-12b-v2-vl-bf16","name":"NVIDIA-Nemotron-Nano-12B-v2-VL-BF16","hf":"nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-Nano-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-10-21","updated":"2026-08-25","gated":false,"params":{"total":13.182,"active":null,"src":"safetensors","q":null,"stTotal":13.182},"moe":false,"ctx":131072,"arch":{"L":62,"attn":6,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.2,"32768":0.81,"131072":3.22},"mem":{"bf16":{"w":26.36,"t":29.7},"fp8":{"w":14.01,"t":16.1},"q4":{"w":7.99,"t":9.5}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":26.36,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16","kind":"BF16"},{"id":"nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nvidia-nemotron-nano-12b-v2-vl-bf16"},{"id":"nvidia-nemotron-parse-v1-2","name":"NVIDIA-Nemotron-Parse-v1.2","hf":"nvidia/NVIDIA-Nemotron-Parse-v1.2","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-Parse","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2026-02-18","updated":"2026-10-20","gated":false,"params":{"total":0.936,"active":null,"src":"safetensors","q":null,"stTotal":0.936},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.87,"t":2.6},"fp8":{"w":0.99,"t":1.6},"q4":{"w":0.57,"t":1.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.75,"native":"F32","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-Parse-v1.2","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-Parse-v1.2","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Parse-v1.2"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Parse-v1.2/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nvidia-nemotron-parse-v1-2"},{"id":"nvidia-nemotron-parse-v1-1","name":"NVIDIA-Nemotron-Parse-v1.1","hf":"nvidia/NVIDIA-Nemotron-Parse-v1.1","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-Parse","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2025-11-15","updated":"2026-10-20","gated":false,"params":{"total":0.957,"active":null,"src":"safetensors","q":null,"stTotal":0.957},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.91,"t":2.6},"fp8":{"w":1.02,"t":1.6},"q4":{"w":0.58,"t":1.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.83,"native":"F32","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-Parse-v1.1","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-Parse-v1.1","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Parse-v1.1"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Parse-v1.1/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nvidia-nemotron-parse-v1-1"},{"id":"nvidia-nemotron-parse-2-0","name":"NVIDIA-Nemotron-Parse-2.0","hf":"nvidia/NVIDIA-Nemotron-Parse-2.0","org":"nvidia","family":"nemotron","series":"NVIDIA-Nemotron-Parse-2.0","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2026-06-30","updated":"2026-10-20","gated":false,"params":{"total":0.903,"active":null,"src":"safetensors","q":null,"stTotal":0.903},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.81,"t":2.5},"fp8":{"w":0.96,"t":1.6},"q4":{"w":0.55,"t":1.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.61,"native":"F32","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Parse-2.0/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-Nemotron-Parse-2.0","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-Nemotron-Parse-2.0","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Parse-2.0"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Parse-2.0/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/nvidia/NVIDIA-Nemotron-Parse-2.0/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nvidia-nemotron-parse-2-0"},{"id":"nvidia-nemotronlabs-voicechat-11b","name":"NVIDIA-NemotronLabs-VoiceChat-11B","hf":"nvidia/NVIDIA-NemotronLabs-VoiceChat-11B","org":"nvidia","family":"nemotron","series":"NVIDIA-NemotronLabs-VoiceChat","task":"llm","pipeline":null,"tags":[],"released":"2026-07-29","updated":"2026-09-22","gated":false,"params":{"total":11.095,"active":null,"src":"safetensors","q":null,"stTotal":11.095},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":22.19,"t":24.9},"fp8":{"w":11.79,"t":13.5},"q4":{"w":6.73,"t":7.9}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":44.38,"native":"F32","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/NVIDIA-NemotronLabs-VoiceChat-11B","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/NVIDIA-NemotronLabs-VoiceChat-11B","u":"https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B"},{"t":"config.json","u":"https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nvidia-nemotronlabs-voicechat-11b"},{"id":"nemotron-3-embed-1b-bf16","name":"Nemotron-3-Embed-1B-BF16","hf":"nvidia/Nemotron-3-Embed-1B-BF16","org":"nvidia","family":"nemotron","series":"Nemotron-3-Embed","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2026-07-14","updated":"2026-08-27","gated":false,"params":{"total":1.141,"active":null,"src":"safetensors","q":null,"stTotal":1.141},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":2.28,"t":3},"fp8":{"w":1.21,"t":1.8},"q4":{"w":0.69,"t":1.3}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.28,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-3-Embed-1B-BF16","kind":"BF16"},{"id":"nvidia/Nemotron-3-Embed-1B-NVFP4","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-3-Embed-1B-BF16","u":"https://huggingface.co/nvidia/Nemotron-3-Embed-1B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-3-Embed-1B-BF16/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-3-embed-1b-bf16"},{"id":"nemotron-3-embed-8b-bf16","name":"Nemotron-3-Embed-8B-BF16","hf":"nvidia/Nemotron-3-Embed-8B-BF16","org":"nvidia","family":"nemotron","series":"Nemotron-3-Embed","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2026-07-14","updated":"2026-08-28","gated":false,"params":{"total":7.953,"active":null,"src":"safetensors","q":null,"stTotal":7.953},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":15.91,"t":18},"fp8":{"w":8.45,"t":9.8},"q4":{"w":4.82,"t":5.8}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.91,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-3-Embed-8B-BF16","kind":"BF16"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-3-Embed-8B-BF16","u":"https://huggingface.co/nvidia/Nemotron-3-Embed-8B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-3-Embed-8B-BF16/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-3-embed-8b-bf16"},{"id":"nemotron-3-labs-ultra-math-rl","name":"Nemotron-3-Labs-Ultra-Math-RL","hf":"nvidia/Nemotron-3-Labs-Ultra-Math-RL","org":"nvidia","family":"nemotron","series":"Nemotron-3-Labs-Ultra-Math-RL","task":"llm","pipeline":"text-generation","tags":["reasoning","math"],"released":"2026-09-02","updated":"2026-09-11","gated":false,"params":{"total":550,"active":55,"src":"card","q":"Number of model parameters: 550B Total / 55B Active","stTotal":560.525},"moe":true,"ctx":262144,"arch":{"L":108,"attn":12,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4,"131072":1.61},"mem":{"bf16":{"w":1100,"t":1210.6},"fp8":{"w":584.38,"t":643.4},"q4":{"w":333.44,"t":367.4}},"fits":{"bf16":{"gpu":"8xb200","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":1121.06,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-3-Labs-Ultra-Math-RL","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-3-Labs-Ultra-Math-RL","u":"https://huggingface.co/nvidia/Nemotron-3-Labs-Ultra-Math-RL"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-3-Labs-Ultra-Math-RL/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/nemotron-3-labs-ultra-math-rl/"},{"id":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","name":"Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","hf":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","org":"nvidia","family":"nemotron","series":"Nemotron-3-Nano-Omni-Reasoning","task":"omni","pipeline":"any-to-any","tags":["reasoning"],"released":"2026-04-20","updated":"2026-08-24","gated":false,"params":{"total":33.016,"active":3,"src":"safetensors","q":null,"stTotal":33.016},"moe":true,"ctx":262144,"arch":{"L":52,"attn":6,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.05,"32768":0.2,"131072":0.81},"mem":{"bf16":{"w":66.03,"t":73.2},"fp8":{"w":35.08,"t":39.1},"q4":{"w":20.02,"t":22.6}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":66.03,"native":"BF16","license":{"id":"nvidia-open-model-agreement","name":"nvidia-open-model-agreement","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-agreement/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8","kind":"FP8"},{"id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","kind":"BF16"},{"id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","u":"https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-agreement/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-3-nano-omni-30b-a3b-reasoning-bf16"},{"id":"nemotron-3-5-embed-1b-bf16","name":"Nemotron-3.5-Embed-1B-BF16","hf":"nvidia/Nemotron-3.5-Embed-1B-BF16","org":"nvidia","family":"nemotron","series":"Nemotron-3.5-Embed","task":"embedding","pipeline":"visual-document-retrieval","tags":[],"released":"2026-10-07","updated":"2026-10-21","gated":false,"params":{"total":1.555,"active":null,"src":"safetensors","q":null,"stTotal":1.555},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":3.11,"t":3.9},"fp8":{"w":1.65,"t":2.3},"q4":{"w":0.94,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.11,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-3.5-Embed-1B-BF16","kind":"BF16"},{"id":"nvidia/Nemotron-3.5-Embed-1B-NVFP4","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-3.5-Embed-1B-BF16","u":"https://huggingface.co/nvidia/Nemotron-3.5-Embed-1B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-3.5-Embed-1B-BF16/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/nemotron-3-5-embed-1b-bf16/"},{"id":"nemotron-3-5-embed-8b-bf16","name":"Nemotron-3.5-Embed-8B-BF16","hf":"nvidia/Nemotron-3.5-Embed-8B-BF16","org":"nvidia","family":"nemotron","series":"Nemotron-3.5-Embed","task":"embedding","pipeline":"visual-document-retrieval","tags":[],"released":"2026-10-07","updated":"2026-10-21","gated":false,"params":{"total":8.381,"active":null,"src":"safetensors","q":null,"stTotal":8.381},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":16.76,"t":18.9},"fp8":{"w":8.9,"t":10.3},"q4":{"w":5.08,"t":6.1}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.76,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-3.5-Embed-8B-BF16","kind":"BF16"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-3.5-Embed-8B-BF16","u":"https://huggingface.co/nvidia/Nemotron-3.5-Embed-8B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-3.5-Embed-8B-BF16/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/nemotron-3-5-embed-8b-bf16/"},{"id":"nemotron-3-5-parse","name":"Nemotron-3.5-Parse","hf":"nvidia/Nemotron-3.5-Parse","org":"nvidia","family":"nemotron","series":"Nemotron-3.5-Parse","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2026-09-03","updated":"2026-10-21","gated":false,"params":{"total":0.631,"active":null,"src":"safetensors","q":null,"stTotal":0.631},"moe":false,"ctx":16384,"arch":{"L":10,"attn":10,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.17},"mem":{"bf16":{"w":1.26,"t":2.1},"fp8":{"w":0.67,"t":1.4},"q4":{"w":0.38,"t":1.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.52,"native":"F32","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://huggingface.co/nvidia/Nemotron-3.5-Parse/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-3.5-Parse","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-3.5-Parse","u":"https://huggingface.co/nvidia/Nemotron-3.5-Parse"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-3.5-Parse/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/nvidia/Nemotron-3.5-Parse/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/nemotron-3-5-parse/"},{"id":"nemotron-3-5-rerank-8b-bf16","name":"Nemotron-3.5-Rerank-8B-BF16","hf":"nvidia/Nemotron-3.5-Rerank-8B-BF16","org":"nvidia","family":"nemotron","series":"Nemotron-3.5-Rerank","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2026-10-15","updated":"2026-10-21","gated":false,"params":{"total":8.381,"active":null,"src":"safetensors","q":null,"stTotal":8.381},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":16.76,"t":18.9},"fp8":{"w":8.9,"t":10.3},"q4":{"w":5.08,"t":6.1}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.76,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-3.5-Rerank-8B-BF16","kind":"BF16"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-3.5-Rerank-8B-BF16","u":"https://huggingface.co/nvidia/Nemotron-3.5-Rerank-8B-BF16"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-3.5-Rerank-8B-BF16/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/nemotron-3-5-rerank-8b-bf16/"},{"id":"nemotron-4-mini-hindi-4b-instruct","name":"Nemotron-4-Mini-Hindi-4B-Instruct","hf":"nvidia/Nemotron-4-Mini-Hindi-4B-Instruct","org":"nvidia","family":"nemotron","series":"Nemotron-4-Mini-Hindi","task":"llm","pipeline":null,"tags":[],"released":"2024-10-22","updated":"2025-08-20","gated":false,"params":{"total":4.191,"active":null,"src":"safetensors","q":null,"stTotal":4.191},"moe":false,"ctx":4096,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07},"mem":{"bf16":{"w":8.38,"t":10.8},"fp8":{"w":4.45,"t":6.5},"q4":{"w":2.54,"t":4.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.38,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/Nemotron-4-Mini-Hindi-4B-Instruct","kind":"Instruct"},{"id":"nvidia/Nemotron-4-Mini-Hindi-4B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-4-Mini-Hindi-4B-Instruct","u":"https://huggingface.co/nvidia/Nemotron-4-Mini-Hindi-4B-Instruct"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-4-Mini-Hindi-4B-Instruct/blob/main/config.json"},{"t":"License","u":"https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-4-mini-hindi-4b-instruct"},{"id":"nemotron-cascade-2-30b-a3b","name":"Nemotron-Cascade-2-30B-A3B","hf":"nvidia/Nemotron-Cascade-2-30B-A3B","org":"nvidia","family":"nemotron","series":"Nemotron-Cascade-2","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-03-18","updated":"2026-07-09","gated":false,"params":{"total":31.578,"active":3,"src":"safetensors","q":null,"stTotal":31.578},"moe":true,"ctx":262144,"arch":{"L":52,"attn":6,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.05,"32768":0.2,"131072":0.81},"mem":{"bf16":{"w":63.16,"t":70},"fp8":{"w":33.55,"t":37.5},"q4":{"w":19.14,"t":21.6}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":63.16,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"nemotron-cascade-2:30b-a3b","url":"https://ollama.com/library/nemotron-cascade-2"}],"variants":[{"id":"nvidia/Nemotron-Cascade-2-30B-A3B","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-Cascade-2-30B-A3B","u":"https://huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"},{"t":"Ollama library · nemotron-cascade-2","u":"https://ollama.com/library/nemotron-cascade-2"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-cascade-2-30b-a3b"},{"id":"nemotron-cascade-8b-thinking","name":"Nemotron-Cascade-8B-Thinking","hf":"nvidia/Nemotron-Cascade-8B-Thinking","org":"nvidia","family":"nemotron","series":"Nemotron-Cascade-Thinking","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-12-08","updated":"2026-01-01","gated":false,"params":{"total":8.191,"active":null,"src":"safetensors","q":null,"stTotal":8.191},"moe":false,"ctx":32768,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":16.38,"t":19.7},"fp8":{"w":8.7,"t":11.3},"q4":{"w":4.97,"t":7.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.38,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-Cascade-8B-Thinking","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-Cascade-8B-Thinking","u":"https://huggingface.co/nvidia/Nemotron-Cascade-8B-Thinking"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-Cascade-8B-Thinking/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-cascade-8b-thinking"},{"id":"nemotron-cascade-14b-thinking","name":"Nemotron-Cascade-14B-Thinking","hf":"nvidia/Nemotron-Cascade-14B-Thinking","org":"nvidia","family":"nemotron","series":"Nemotron-Cascade-Thinking","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-12-08","updated":"2026-01-01","gated":false,"params":{"total":14.768,"active":null,"src":"safetensors","q":null,"stTotal":14.768},"moe":false,"ctx":32768,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37},"mem":{"bf16":{"w":29.54,"t":34.3},"fp8":{"w":15.69,"t":19.1},"q4":{"w":8.95,"t":11.7}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":29.54,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-Cascade-14B-Thinking","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-Cascade-14B-Thinking","u":"https://huggingface.co/nvidia/Nemotron-Cascade-14B-Thinking"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-Cascade-14B-Thinking/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-cascade-14b-thinking"},{"id":"nemotron-flash-1b","name":"Nemotron-Flash-1B","hf":"nvidia/Nemotron-Flash-1B","org":"nvidia","family":"nemotron","series":"Nemotron-Flash","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-11-06","updated":"2026-01-09","gated":false,"params":{"total":0.965,"active":null,"src":"safetensors","q":null,"stTotal":0.965},"moe":true,"ctx":36000,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.4,"32768":1.61},"mem":{"bf16":{"w":1.93,"t":3},"fp8":{"w":1.03,"t":2},"q4":{"w":0.59,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.93,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/Nemotron-Flash-1B","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-Flash-1B","u":"https://huggingface.co/nvidia/Nemotron-Flash-1B"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-Flash-1B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-flash-1b"},{"id":"nemotron-h-4b-instruct-128k","name":"Nemotron-H-4B-Instruct-128K","hf":"nvidia/Nemotron-H-4B-Instruct-128K","org":"nvidia","family":"nemotron","series":"Nemotron-H-128K","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-15","updated":"2025-10-24","gated":false,"params":{"total":4.489,"active":null,"src":"safetensors","q":null,"stTotal":4.489},"moe":false,"ctx":131072,"arch":{"L":52,"attn":4,"slide":0,"win":null,"kvElems":1536,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4,"131072":1.61},"mem":{"bf16":{"w":8.98,"t":10.5},"fp8":{"w":4.77,"t":5.8},"q4":{"w":2.72,"t":3.6}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.98,"native":"BF16","license":{"id":"nvidia-internal-scientific-research-and-development-model-license","name":"nvidia-internal-scientific-research-and-development-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-H-4B-Instruct-128K","kind":"Instruct"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-H-4B-Instruct-128K","u":"https://huggingface.co/nvidia/Nemotron-H-4B-Instruct-128K"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-H-4B-Instruct-128K/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-h-4b-instruct-128k"},{"id":"nemotron-h-4b-base-8k","name":"Nemotron-H-4B-Base-8K","hf":"nvidia/Nemotron-H-4B-Base-8K","org":"nvidia","family":"nemotron","series":"Nemotron-H-8K","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-03-20","updated":"2025-10-24","gated":false,"params":{"total":4.489,"active":null,"src":"safetensors","q":null,"stTotal":4.489},"moe":false,"ctx":8192,"arch":{"L":52,"attn":4,"slide":0,"win":null,"kvElems":1536,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1},"mem":{"bf16":{"w":8.98,"t":10.5},"fp8":{"w":4.77,"t":5.8},"q4":{"w":2.72,"t":3.6}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.98,"native":"BF16","license":{"id":"nvidia-internal-scientific-research-and-development-model-license","name":"nvidia-internal-scientific-research-and-development-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-H-4B-Base-8K","kind":"Base"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-H-4B-Base-8K","u":"https://huggingface.co/nvidia/Nemotron-H-4B-Base-8K"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-H-4B-Base-8K/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-h-4b-base-8k"},{"id":"nemotron-h-8b-base-8k","name":"Nemotron-H-8B-Base-8K","hf":"nvidia/Nemotron-H-8B-Base-8K","org":"nvidia","family":"nemotron","series":"Nemotron-H-8K","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-03-19","updated":"2025-08-21","gated":false,"params":{"total":8.101,"active":null,"src":"safetensors","q":null,"stTotal":8.101},"moe":false,"ctx":8192,"arch":{"L":52,"attn":4,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.13},"mem":{"bf16":{"w":16.2,"t":18.5},"fp8":{"w":8.61,"t":10.1},"q4":{"w":4.91,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.2,"native":"BF16","license":{"id":"nvidia-internal-scientific-research-and-development-model-license","name":"nvidia-internal-scientific-research-and-development-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-H-8B-Base-8K","kind":"Base"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-H-8B-Base-8K","u":"https://huggingface.co/nvidia/Nemotron-H-8B-Base-8K"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-H-8B-Base-8K/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-h-8b-base-8k"},{"id":"nemotron-h-56b-base-8k","name":"Nemotron-H-56B-Base-8K","hf":"nvidia/Nemotron-H-56B-Base-8K","org":"nvidia","family":"nemotron","series":"Nemotron-H-8K","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-08","updated":"2025-08-21","gated":false,"params":{"total":56.324,"active":null,"src":"safetensors","q":null,"stTotal":56.324},"moe":false,"ctx":8192,"arch":{"L":118,"attn":10,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.34},"mem":{"bf16":{"w":112.65,"t":124.8},"fp8":{"w":59.84,"t":66.7},"q4":{"w":34.15,"t":38.4}},"fits":{"bf16":{"gpu":"h200","mac":"mac256"},"fp8":{"gpu":"h100","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac64"}},"disk":112.65,"native":"BF16","license":{"id":"nvidia-internal-scientific-research-and-development-model-license","name":"nvidia-internal-scientific-research-and-development-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-H-56B-Base-8K","kind":"Base"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-H-56B-Base-8K","u":"https://huggingface.co/nvidia/Nemotron-H-56B-Base-8K"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-H-56B-Base-8K/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-h-56b-base-8k"},{"id":"nemotron-h-8b-reasoning-128k","name":"Nemotron-H-8B-Reasoning-128K","hf":"nvidia/Nemotron-H-8B-Reasoning-128K","org":"nvidia","family":"nemotron","series":"Nemotron-H-Reasoning-128K","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-06-05","updated":"2025-07-11","gated":false,"params":{"total":8.101,"active":null,"src":"safetensors","q":null,"stTotal":8.101},"moe":false,"ctx":131072,"arch":{"L":52,"attn":4,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.13,"32768":0.54,"131072":2.15},"mem":{"bf16":{"w":16.2,"t":18.5},"fp8":{"w":8.61,"t":10.1},"q4":{"w":4.91,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.2,"native":"BF16","license":{"id":"nvidia-internal-scientific-research-and-development-model-license","name":"nvidia-internal-scientific-research-and-development-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/","cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"nvidia/Nemotron-H-8B-Reasoning-128K","kind":"main"},{"id":"nvidia/Nemotron-H-8B-Reasoning-128K-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-H-8B-Reasoning-128K","u":"https://huggingface.co/nvidia/Nemotron-H-8B-Reasoning-128K"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-H-8B-Reasoning-128K/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-h-8b-reasoning-128k"},{"id":"nemotron-labs-audex-2b","name":"Nemotron-Labs-Audex-2B","hf":"nvidia/Nemotron-Labs-Audex-2B","org":"nvidia","family":"nemotron","series":"Nemotron-Labs-Audex","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-07-06","updated":"2026-08-18","gated":false,"params":{"total":2,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":4,"t":4.9},"fp8":{"w":2.12,"t":2.8},"q4":{"w":1.21,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":12.15,"native":null,"license":{"id":"nvidia-oneway-noncommercial-license","name":"nvidia-oneway-noncommercial-license","link":"https://huggingface.co/nvidia/Nemotron-Labs-Audex-2B/blob/main/license/NVIDIA-OneWay-Noncommercial-License.docx","cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-Labs-Audex-2B","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-Labs-Audex-2B","u":"https://huggingface.co/nvidia/Nemotron-Labs-Audex-2B"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-Labs-Audex-2B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/nvidia/Nemotron-Labs-Audex-2B/blob/main/license/NVIDIA-OneWay-Noncommercial-License.docx"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-labs-audex-2b"},{"id":"nemotron-labs-diffusion-3b","name":"Nemotron-Labs-Diffusion-3B","hf":"nvidia/Nemotron-Labs-Diffusion-3B","org":"nvidia","family":"nemotron","series":"Nemotron-Labs-Diffusion","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-03-02","updated":"2026-06-03","gated":false,"params":{"total":3.832,"active":null,"src":"safetensors","q":null,"stTotal":3.832},"moe":false,"ctx":262144,"arch":{"L":26,"attn":26,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.87,"32768":3.49,"131072":13.96},"mem":{"bf16":{"w":7.66,"t":9.8},"fp8":{"w":4.07,"t":5.8},"q4":{"w":2.32,"t":3.9}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.66,"native":"BF16","license":{"id":"nvidia-nemotron-open-model-license","name":"nvidia-nemotron-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","cls":"cond"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-Labs-Diffusion-3B","kind":"main"},{"id":"nvidia/Nemotron-Labs-Diffusion-3B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-Labs-Diffusion-3B","u":"https://huggingface.co/nvidia/Nemotron-Labs-Diffusion-3B"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-Labs-Diffusion-3B/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-labs-diffusion-3b"},{"id":"nemotron-labs-diffusion-8b","name":"Nemotron-Labs-Diffusion-8B","hf":"nvidia/Nemotron-Labs-Diffusion-8B","org":"nvidia","family":"nemotron","series":"Nemotron-Labs-Diffusion","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-03-18","updated":"2026-06-03","gated":false,"params":{"total":8.49,"active":null,"src":"safetensors","q":null,"stTotal":8.49},"moe":false,"ctx":262144,"arch":{"L":34,"attn":34,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.14,"32768":4.56,"131072":18.25},"mem":{"bf16":{"w":16.98,"t":20.3},"fp8":{"w":9.02,"t":11.6},"q4":{"w":5.15,"t":7.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":16.98,"native":"BF16","license":{"id":"nvidia-nemotron-open-model-license","name":"nvidia-nemotron-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","cls":"cond"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-Labs-Diffusion-8B-Base","kind":"Base"},{"id":"nvidia/Nemotron-Labs-Diffusion-8B","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-Labs-Diffusion-8B","u":"https://huggingface.co/nvidia/Nemotron-Labs-Diffusion-8B"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-Labs-Diffusion-8B/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-labs-diffusion-8b"},{"id":"nemotron-labs-diffusion-14b","name":"Nemotron-Labs-Diffusion-14B","hf":"nvidia/Nemotron-Labs-Diffusion-14B","org":"nvidia","family":"nemotron","series":"Nemotron-Labs-Diffusion","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-04-22","updated":"2026-06-03","gated":false,"params":{"total":13.506,"active":null,"src":"safetensors","q":null,"stTotal":13.506},"moe":false,"ctx":262144,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":27.01,"t":31.6},"fp8":{"w":14.35,"t":17.6},"q4":{"w":8.19,"t":10.8}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac24"}},"disk":27.01,"native":"BF16","license":{"id":"nvidia-nemotron-open-model-license","name":"nvidia-nemotron-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/","cls":"cond"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-Labs-Diffusion-14B","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-Labs-Diffusion-14B","u":"https://huggingface.co/nvidia/Nemotron-Labs-Diffusion-14B"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-Labs-Diffusion-14B/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-labs-diffusion-14b"},{"id":"nemotron-labs-diffusion-vlm-8b","name":"Nemotron-Labs-Diffusion-VLM-8B","hf":"nvidia/Nemotron-Labs-Diffusion-VLM-8B","org":"nvidia","family":"nemotron","series":"Nemotron-Labs-Diffusion-VLM","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-05-08","updated":"2026-06-03","gated":false,"params":{"total":8.918,"active":null,"src":"safetensors","q":null,"stTotal":8.918},"moe":false,"ctx":262144,"arch":{"L":34,"attn":34,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.14,"32768":4.56,"131072":18.25},"mem":{"bf16":{"w":17.84,"t":21.3},"fp8":{"w":9.48,"t":12.1},"q4":{"w":5.41,"t":7.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":17.84,"native":"BF16","license":{"id":"nscl-v1","name":"nscl-v1","link":null,"cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-Labs-Diffusion-VLM-8B","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-Labs-Diffusion-VLM-8B","u":"https://huggingface.co/nvidia/Nemotron-Labs-Diffusion-VLM-8B"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-Labs-Diffusion-VLM-8B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-labs-diffusion-vlm-8b"},{"id":"nemotron-mini-4b-instruct","name":"Nemotron-Mini-4B-Instruct","hf":"nvidia/Nemotron-Mini-4B-Instruct","org":"nvidia","family":"nemotron","series":"Nemotron-Mini","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-10","updated":"2025-02-14","gated":false,"params":{"total":4,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":4096,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07},"mem":{"bf16":{"w":8,"t":10.4},"fp8":{"w":4.25,"t":6.2},"q4":{"w":2.42,"t":4.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.77,"native":null,"license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"nemotron-mini:4b","url":"https://ollama.com/library/nemotron-mini"}],"variants":[{"id":"nvidia/Nemotron-Mini-4B-Instruct","kind":"Instruct"},{"id":"nvidia/Nemotron-Mini-4B-Instruct-ONNX-INT4","kind":"Instruct/ONNX/INT4"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-Mini-4B-Instruct","u":"https://huggingface.co/nvidia/Nemotron-Mini-4B-Instruct"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-Mini-4B-Instruct/blob/main/config.json"},{"t":"License","u":"https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf"},{"t":"Ollama library · nemotron-mini","u":"https://ollama.com/library/nemotron-mini"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-mini-4b-instruct"},{"id":"nemotron-orchestrator-8b","name":"Nemotron-Orchestrator-8B","hf":"nvidia/Nemotron-Orchestrator-8B","org":"nvidia","family":"nemotron","series":"Nemotron-Orchestrator","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-11-25","updated":"2025-12-02","gated":false,"params":{"total":8.191,"active":null,"src":"safetensors","q":null,"stTotal":8.191},"moe":false,"ctx":40960,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":16.38,"t":19.7},"fp8":{"w":8.7,"t":11.3},"q4":{"w":4.97,"t":7.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":32.76,"native":"F32","license":{"id":null,"name":null,"link":"https://huggingface.co/nvidia/Nemotron-Orchestrator-8B/blob/main/LICENSE","cls":"unknown"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/Nemotron-Orchestrator-8B","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/Nemotron-Orchestrator-8B","u":"https://huggingface.co/nvidia/Nemotron-Orchestrator-8B"},{"t":"config.json","u":"https://huggingface.co/nvidia/Nemotron-Orchestrator-8B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/nvidia/Nemotron-Orchestrator-8B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-orchestrator-8b"},{"id":"openreasoning-nemotron-7b","name":"OpenReasoning-Nemotron-7B","hf":"nvidia/OpenReasoning-Nemotron-7B","org":"nvidia","family":"nemotron","series":"OpenReasoning-Nemotron","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-07-15","updated":"2025-09-16","gated":false,"params":{"total":7.616,"active":null,"src":"safetensors","q":null,"stTotal":7.616},"moe":false,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88,"131072":7.52},"mem":{"bf16":{"w":15.23,"t":17.7},"fp8":{"w":8.09,"t":9.9},"q4":{"w":4.62,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.23,"native":"BF16","license":{"id":"cc-by-4.0","name":"CC-BY-4.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/OpenReasoning-Nemotron-7B","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/OpenReasoning-Nemotron-7B","u":"https://huggingface.co/nvidia/OpenReasoning-Nemotron-7B"},{"t":"config.json","u":"https://huggingface.co/nvidia/OpenReasoning-Nemotron-7B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-openreasoning-nemotron-7b"},{"id":"llama-embed-nemotron-8b","name":"llama-embed-nemotron-8b","hf":"nvidia/llama-embed-nemotron-8b","org":"nvidia","family":"nemotron","series":"llama-embed-nemotron","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2025-10-07","updated":"2026-04-23","gated":false,"params":{"total":7.505,"active":null,"src":"safetensors","q":null,"stTotal":7.505},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":15.01,"t":17},"fp8":{"w":7.97,"t":9.3},"q4":{"w":4.55,"t":5.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.01,"native":"BF16","license":{"id":"customized-nscl-v1","name":"customized-nscl-v1","link":"https://huggingface.co/nvidia/llama-embed-nemotron-8b/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"nvidia/llama-embed-nemotron-8b","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/llama-embed-nemotron-8b","u":"https://huggingface.co/nvidia/llama-embed-nemotron-8b"},{"t":"config.json","u":"https://huggingface.co/nvidia/llama-embed-nemotron-8b/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/nvidia/llama-embed-nemotron-8b/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-embed-nemotron-8b"},{"id":"llama-nemotron-colembed-vl-3b-v2","name":"llama-nemotron-colembed-vl-3b-v2","hf":"nvidia/llama-nemotron-colembed-vl-3b-v2","org":"nvidia","family":"nemotron","series":"llama-nemotron-colembed-vl","task":"embedding","pipeline":"visual-document-retrieval","tags":[],"released":"2026-01-14","updated":"2026-05-20","gated":false,"params":{"total":4.405,"active":null,"src":"safetensors","q":null,"stTotal":4.405},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":8.81,"t":10.2},"fp8":{"w":4.68,"t":5.6},"q4":{"w":2.67,"t":3.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.81,"native":"BF16","license":{"id":"customized-nscl-v1","name":"customized-nscl-v1","link":"https://huggingface.co/nvidia/llama-nemotron-colembed-vl-3b-v2/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/llama-nemotron-colembed-vl-3b-v2","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/llama-nemotron-colembed-vl-3b-v2","u":"https://huggingface.co/nvidia/llama-nemotron-colembed-vl-3b-v2"},{"t":"config.json","u":"https://huggingface.co/nvidia/llama-nemotron-colembed-vl-3b-v2/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/nvidia/llama-nemotron-colembed-vl-3b-v2/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-nemotron-colembed-vl-3b-v2"},{"id":"llama-nemotron-embed-1b-v2","name":"llama-nemotron-embed-1b-v2","hf":"nvidia/llama-nemotron-embed-1b-v2","org":"nvidia","family":"nemotron","series":"llama-nemotron-embed","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2025-10-16","updated":"2026-05-20","gated":false,"params":{"total":1.236,"active":null,"src":"safetensors","q":null,"stTotal":1.236},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":2.47,"t":3.2},"fp8":{"w":1.31,"t":1.9},"q4":{"w":0.75,"t":1.3}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.47,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"nvidia/llama-nemotron-embed-1b-v2","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/llama-nemotron-embed-1b-v2","u":"https://huggingface.co/nvidia/llama-nemotron-embed-1b-v2"},{"t":"config.json","u":"https://huggingface.co/nvidia/llama-nemotron-embed-1b-v2/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-nemotron-embed-1b-v2"},{"id":"llama-nemotron-embed-vl-1b-v2","name":"llama-nemotron-embed-vl-1b-v2","hf":"nvidia/llama-nemotron-embed-vl-1b-v2","org":"nvidia","family":"nemotron","series":"llama-nemotron-embed-vl","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2025-12-03","updated":"2026-07-07","gated":false,"params":{"total":1.678,"active":null,"src":"safetensors","q":null,"stTotal":1.678},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":3.36,"t":4.2},"fp8":{"w":1.78,"t":2.5},"q4":{"w":1.02,"t":1.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.36,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"nvidia/llama-nemotron-embed-vl-1b-v2","kind":"main"},{"id":"nvidia/llama-nemotron-embed-vl-1b-v2-fp8","kind":"FP8"}],"sources":[{"t":"Hugging Face · nvidia/llama-nemotron-embed-vl-1b-v2","u":"https://huggingface.co/nvidia/llama-nemotron-embed-vl-1b-v2"},{"t":"config.json","u":"https://huggingface.co/nvidia/llama-nemotron-embed-vl-1b-v2/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-nemotron-embed-vl-1b-v2"},{"id":"llama-nemotron-rerank-1b-v2","name":"llama-nemotron-rerank-1b-v2","hf":"nvidia/llama-nemotron-rerank-1b-v2","org":"nvidia","family":"nemotron","series":"llama-nemotron-rerank","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2025-10-16","updated":"2026-08-26","gated":false,"params":{"total":1.236,"active":null,"src":"safetensors","q":null,"stTotal":1.236},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":2.47,"t":3.2},"fp8":{"w":1.31,"t":1.9},"q4":{"w":0.75,"t":1.3}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.47,"native":"BF16","license":{"id":"openmdw-1.1","name":"OpenMDW-1.1","link":"https://openmdw.ai/license/1-1/","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/llama-nemotron-rerank-1b-v2","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/llama-nemotron-rerank-1b-v2","u":"https://huggingface.co/nvidia/llama-nemotron-rerank-1b-v2"},{"t":"config.json","u":"https://huggingface.co/nvidia/llama-nemotron-rerank-1b-v2/blob/main/config.json"},{"t":"License","u":"https://openmdw.ai/license/1-1/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-nemotron-rerank-1b-v2"},{"id":"llama-nemotron-rerank-vl-1b-v2","name":"llama-nemotron-rerank-vl-1b-v2","hf":"nvidia/llama-nemotron-rerank-vl-1b-v2","org":"nvidia","family":"nemotron","series":"llama-nemotron-rerank-vl","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2025-12-04","updated":"2026-10-01","gated":false,"params":{"total":1.678,"active":null,"src":"safetensors","q":null,"stTotal":1.678},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":3.36,"t":4.2},"fp8":{"w":1.78,"t":2.5},"q4":{"w":1.02,"t":1.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.36,"native":"BF16","license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"nvidia/llama-nemotron-rerank-vl-1b-v2","kind":"main"},{"id":"nvidia/llama-nemotron-rerank-vl-1b-v2-fp8","kind":"FP8"}],"sources":[{"t":"Hugging Face · nvidia/llama-nemotron-rerank-vl-1b-v2","u":"https://huggingface.co/nvidia/llama-nemotron-rerank-vl-1b-v2"},{"t":"config.json","u":"https://huggingface.co/nvidia/llama-nemotron-rerank-vl-1b-v2/blob/main/config.json"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-llama-nemotron-rerank-vl-1b-v2"},{"id":"nemocurator-fineweb-nemotron-4-edu-classifier","name":"nemocurator-fineweb-nemotron-4-edu-classifier","hf":"nvidia/nemocurator-fineweb-nemotron-4-edu-classifier","org":"nvidia","family":"nemotron","series":"nemocurator-fineweb-nemotron-4-edu-classifier","task":"llm","pipeline":null,"tags":[],"released":"2025-02-07","updated":"2025-09-22","gated":false,"params":{"total":0.109,"active":null,"src":"safetensors","q":null,"stTotal":0.109},"moe":false,"ctx":512,"arch":{"L":12,"attn":12,"slide":0,"win":null,"kvElems":1536,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.3},"mem":{"bf16":{"w":0.22,"t":1},"fp8":{"w":0.12,"t":0.9},"q4":{"w":0.07,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.44,"native":"F32","license":{"id":"other","name":"other","link":null,"cls":"custom"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/nemocurator-fineweb-nemotron-4-edu-classifier","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/nemocurator-fineweb-nemotron-4-edu-classifier","u":"https://huggingface.co/nvidia/nemocurator-fineweb-nemotron-4-edu-classifier"},{"t":"config.json","u":"https://huggingface.co/nvidia/nemocurator-fineweb-nemotron-4-edu-classifier/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemocurator-fineweb-nemotron-4-edu-classifier"},{"id":"nemotron-colembed-vl-4b-v2","name":"nemotron-colembed-vl-4b-v2","hf":"nvidia/nemotron-colembed-vl-4b-v2","org":"nvidia","family":"nemotron","series":"nemotron-colembed-vl","task":"embedding","pipeline":"visual-document-retrieval","tags":[],"released":"2026-01-15","updated":"2026-02-21","gated":false,"params":{"total":4.827,"active":null,"src":"safetensors","q":null,"stTotal":4.827},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":9.65,"t":11.1},"fp8":{"w":5.13,"t":6.1},"q4":{"w":2.93,"t":3.7}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":9.65,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":"https://huggingface.co/nvidia/nemotron-colembed-vl-4b-v2/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/nemotron-colembed-vl-4b-v2","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/nemotron-colembed-vl-4b-v2","u":"https://huggingface.co/nvidia/nemotron-colembed-vl-4b-v2"},{"t":"config.json","u":"https://huggingface.co/nvidia/nemotron-colembed-vl-4b-v2/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/nvidia/nemotron-colembed-vl-4b-v2/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-colembed-vl-4b-v2"},{"id":"nemotron-colembed-vl-8b-v2","name":"nemotron-colembed-vl-8b-v2","hf":"nvidia/nemotron-colembed-vl-8b-v2","org":"nvidia","family":"nemotron","series":"nemotron-colembed-vl","task":"embedding","pipeline":"visual-document-retrieval","tags":[],"released":"2026-01-15","updated":"2026-02-21","gated":false,"params":{"total":8.767,"active":null,"src":"safetensors","q":null,"stTotal":8.767},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":17.53,"t":19.8},"fp8":{"w":9.31,"t":10.7},"q4":{"w":5.31,"t":6.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.53,"native":"BF16","license":{"id":"cc-by-nc-4.0","name":"CC-BY-NC-4.0","link":"https://huggingface.co/nvidia/nemotron-colembed-vl-8b-v2/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"nvidia/nemotron-colembed-vl-8b-v2","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/nemotron-colembed-vl-8b-v2","u":"https://huggingface.co/nvidia/nemotron-colembed-vl-8b-v2"},{"t":"config.json","u":"https://huggingface.co/nvidia/nemotron-colembed-vl-8b-v2/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/nvidia/nemotron-colembed-vl-8b-v2/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-colembed-vl-8b-v2"},{"id":"nemotron-ocr-v2","name":"nemotron-ocr-v2","hf":"nvidia/nemotron-ocr-v2","org":"nvidia","family":"nemotron","series":"nemotron-ocr","task":"vlm","pipeline":"image-to-text","tags":["ocr"],"released":"2026-04-01","updated":"2026-05-22","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":0.55,"native":null,"license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[],"variants":[{"id":"nvidia/nemotron-ocr-v2","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/nemotron-ocr-v2","u":"https://huggingface.co/nvidia/nemotron-ocr-v2"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-nemotron-ocr-v2"},{"id":"omni-embed-nemotron-3b","name":"omni-embed-nemotron-3b","hf":"nvidia/omni-embed-nemotron-3b","org":"nvidia","family":"nemotron","series":"omni-embed-nemotron","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2025-09-30","updated":"2026-05-06","gated":false,"params":{"total":4.703,"active":null,"src":"safetensors","q":null,"stTotal":4.703},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":9.41,"t":10.8},"fp8":{"w":5,"t":6},"q4":{"w":2.85,"t":3.6}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":9.41,"native":"BF16","license":{"id":"customized-nscl-v1","name":"customized-nscl-v1","link":"https://huggingface.co/nvidia/omni-embed-nemotron-3b/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"nvidia/omni-embed-nemotron-3b","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/omni-embed-nemotron-3b","u":"https://huggingface.co/nvidia/omni-embed-nemotron-3b"},{"t":"config.json","u":"https://huggingface.co/nvidia/omni-embed-nemotron-3b/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/nvidia/omni-embed-nemotron-3b/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/nemotron/#m-omni-embed-nemotron-3b"},{"id":"canary-1b-v2","name":"canary-1b-v2","hf":"nvidia/canary-1b-v2","org":"nvidia","family":"nv-speech","series":"canary","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-08-04","updated":"2026-08-31","gated":false,"params":{"total":0.979,"active":null,"src":"safetensors","q":null,"stTotal":0.979},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.96,"t":2.7},"fp8":{"w":1.04,"t":1.6},"q4":{"w":0.59,"t":1.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.92,"native":"F32","license":{"id":"cc-by-4.0","name":"CC-BY-4.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"nemo","via":"card"}],"variants":[{"id":"nvidia/canary-1b-v2","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/canary-1b-v2","u":"https://huggingface.co/nvidia/canary-1b-v2"},{"t":"config.json","u":"https://huggingface.co/nvidia/canary-1b-v2/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/nv-speech/#m-canary-1b-v2"},{"id":"canary-180m-flash","name":"canary-180m-flash","hf":"nvidia/canary-180m-flash","org":"nvidia","family":"nv-speech","series":"canary-flash","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-03-11","updated":"2025-03-18","gated":false,"params":{"total":0.18,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.36,"t":0.9},"fp8":{"w":0.19,"t":0.7},"q4":{"w":0.11,"t":0.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.74,"native":null,"license":{"id":"cc-by-4.0","name":"CC-BY-4.0","link":null,"cls":"open"},"runtimes":[{"id":"nemo","via":"card"}],"variants":[{"id":"nvidia/canary-180m-flash","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/canary-180m-flash","u":"https://huggingface.co/nvidia/canary-180m-flash"}],"page":"https://aimap.page/en/models/compute/open-models/family/nv-speech/#m-canary-180m-flash"},{"id":"canary-1b-flash","name":"canary-1b-flash","hf":"nvidia/canary-1b-flash","org":"nvidia","family":"nv-speech","series":"canary-flash","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-03-07","updated":"2026-06-29","gated":false,"params":{"total":0.811,"active":null,"src":"safetensors","q":null,"stTotal":0.811},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.62,"t":2.3},"fp8":{"w":0.86,"t":1.4},"q4":{"w":0.49,"t":1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.24,"native":"F32","license":{"id":"cc-by-4.0","name":"CC-BY-4.0","link":null,"cls":"open"},"runtimes":[{"id":"nemo","via":"card"}],"variants":[{"id":"nvidia/canary-1b-flash","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/canary-1b-flash","u":"https://huggingface.co/nvidia/canary-1b-flash"},{"t":"config.json","u":"https://huggingface.co/nvidia/canary-1b-flash/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/nv-speech/#m-canary-1b-flash"},{"id":"canary-qwen-2-5b","name":"canary-qwen-2.5b","hf":"nvidia/canary-qwen-2.5b","org":"nvidia","family":"nv-speech","series":"canary-qwen","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-06-26","updated":"2026-04-21","gated":false,"params":{"total":2.559,"active":null,"src":"safetensors","q":null,"stTotal":2.559},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":5.12,"t":6.1},"fp8":{"w":2.72,"t":3.5},"q4":{"w":1.55,"t":2.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.12,"native":"BF16","license":{"id":"cc-by-4.0","name":"CC-BY-4.0","link":null,"cls":"open"},"runtimes":[{"id":"nemo","via":"card"}],"variants":[{"id":"nvidia/canary-qwen-2.5b","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/canary-qwen-2.5b","u":"https://huggingface.co/nvidia/canary-qwen-2.5b"},{"t":"config.json","u":"https://huggingface.co/nvidia/canary-qwen-2.5b/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/nv-speech/#m-canary-qwen-2-5b"},{"id":"multitalker-parakeet-streaming-0-6b-v1","name":"multitalker-parakeet-streaming-0.6b-v1","hf":"nvidia/multitalker-parakeet-streaming-0.6b-v1","org":"nvidia","family":"nv-speech","series":"multitalker-parakeet-streaming","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-10-15","updated":"2026-01-28","gated":false,"params":{"total":0.6,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.2,"t":1.8},"fp8":{"w":0.64,"t":1.2},"q4":{"w":0.36,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.49,"native":null,"license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"nemo","via":"card"}],"variants":[{"id":"nvidia/multitalker-parakeet-streaming-0.6b-v1","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/multitalker-parakeet-streaming-0.6b-v1","u":"https://huggingface.co/nvidia/multitalker-parakeet-streaming-0.6b-v1"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nv-speech/#m-multitalker-parakeet-streaming-0-6b-v1"},{"id":"parakeet-tdt-0-6b-v2","name":"parakeet-tdt-0.6b-v2","hf":"nvidia/parakeet-tdt-0.6b-v2","org":"nvidia","family":"nv-speech","series":"parakeet-tdt","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-04-15","updated":"2026-06-29","gated":false,"params":{"total":0.6,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.2,"t":1.8},"fp8":{"w":0.64,"t":1.2},"q4":{"w":0.36,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.47,"native":null,"license":{"id":"cc-by-4.0","name":"CC-BY-4.0","link":null,"cls":"open"},"runtimes":[{"id":"nemo","via":"card"}],"variants":[{"id":"nvidia/parakeet-tdt-0.6b-v2","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/parakeet-tdt-0.6b-v2","u":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2"}],"page":"https://aimap.page/en/models/compute/open-models/family/nv-speech/#m-parakeet-tdt-0-6b-v2"},{"id":"parakeet-tdt-ctc-110m","name":"parakeet-tdt_ctc-110m","hf":"nvidia/parakeet-tdt_ctc-110m","org":"nvidia","family":"nv-speech","series":"parakeet-tdt_ctc","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2024-09-17","updated":"2025-02-18","gated":false,"params":{"total":0.11,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.22,"t":0.7},"fp8":{"w":0.12,"t":0.6},"q4":{"w":0.07,"t":0.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.46,"native":null,"license":{"id":"cc-by-4.0","name":"CC-BY-4.0","link":null,"cls":"open"},"runtimes":[{"id":"nemo","via":"card"}],"variants":[{"id":"nvidia/parakeet-tdt_ctc-110m","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/parakeet-tdt_ctc-110m","u":"https://huggingface.co/nvidia/parakeet-tdt_ctc-110m"}],"page":"https://aimap.page/en/models/compute/open-models/family/nv-speech/#m-parakeet-tdt-ctc-110m"},{"id":"parakeet-tdt-ctc-1-1b","name":"parakeet-tdt_ctc-1.1b","hf":"nvidia/parakeet-tdt_ctc-1.1b","org":"nvidia","family":"nv-speech","series":"parakeet-tdt_ctc","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2024-05-07","updated":"2025-02-18","gated":false,"params":{"total":1.1,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":2.2,"t":2.9},"fp8":{"w":1.17,"t":1.8},"q4":{"w":0.67,"t":1.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.29,"native":null,"license":{"id":"cc-by-4.0","name":"CC-BY-4.0","link":null,"cls":"open"},"runtimes":[{"id":"nemo","via":"card"}],"variants":[{"id":"nvidia/parakeet-tdt_ctc-1.1b","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/parakeet-tdt_ctc-1.1b","u":"https://huggingface.co/nvidia/parakeet-tdt_ctc-1.1b"}],"page":"https://aimap.page/en/models/compute/open-models/family/nv-speech/#m-parakeet-tdt-ctc-1-1b"},{"id":"parakeet-tdt-ctc-0-6b-ja","name":"parakeet-tdt_ctc-0.6b-ja","hf":"nvidia/parakeet-tdt_ctc-0.6b-ja","org":"nvidia","family":"nv-speech","series":"parakeet-tdt_ctc-ja","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2024-05-13","updated":"2025-02-18","gated":false,"params":{"total":0.6,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.2,"t":1.8},"fp8":{"w":0.64,"t":1.2},"q4":{"w":0.36,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.49,"native":null,"license":{"id":"cc-by-4.0","name":"CC-BY-4.0","link":null,"cls":"open"},"runtimes":[{"id":"nemo","via":"card"}],"variants":[{"id":"nvidia/parakeet-tdt_ctc-0.6b-ja","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/parakeet-tdt_ctc-0.6b-ja","u":"https://huggingface.co/nvidia/parakeet-tdt_ctc-0.6b-ja"}],"page":"https://aimap.page/en/models/compute/open-models/family/nv-speech/#m-parakeet-tdt-ctc-0-6b-ja"},{"id":"parakeet-unified-en-0-6b","name":"parakeet-unified-en-0.6b","hf":"nvidia/parakeet-unified-en-0.6b","org":"nvidia","family":"nv-speech","series":"parakeet-unified-en","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-04-07","updated":"2026-06-09","gated":false,"params":{"total":0.6,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.2,"t":1.8},"fp8":{"w":0.64,"t":1.2},"q4":{"w":0.36,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.47,"native":null,"license":{"id":"nvidia-open-model-license","name":"nvidia-open-model-license","link":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","cls":"cond"},"runtimes":[{"id":"nemo","via":"card"}],"variants":[{"id":"nvidia/parakeet-unified-en-0.6b","kind":"main"}],"sources":[{"t":"Hugging Face · nvidia/parakeet-unified-en-0.6b","u":"https://huggingface.co/nvidia/parakeet-unified-en-0.6b"},{"t":"License","u":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/"}],"page":"https://aimap.page/en/models/compute/open-models/family/nv-speech/#m-parakeet-unified-en-0-6b"},{"id":"flexolmo-7x7b-1t","name":"FlexOlmo-7x7B-1T","hf":"allenai/FlexOlmo-7x7B-1T","org":"allenai","family":"olmo","series":"FlexOlmo","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-11","updated":"2026-03-02","gated":false,"params":{"total":1000,"active":null,"src":"name","q":null,"stTotal":null},"moe":true,"ctx":4096,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":4.29},"mem":{"bf16":{"w":2000,"t":2204.8},"fp8":{"w":1062.5,"t":1173.5},"q4":{"w":606.25,"t":671.7}},"fits":{"bf16":{"gpu":"2x8xb300","mac":null},"fp8":{"gpu":"8xb200","mac":null},"q4":{"gpu":"8xh200","mac":null}},"disk":133.08,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/FlexOlmo-7x7B-1T","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/FlexOlmo-7x7B-1T","u":"https://huggingface.co/allenai/FlexOlmo-7x7B-1T"},{"t":"config.json","u":"https://huggingface.co/allenai/FlexOlmo-7x7B-1T/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/flexolmo-7x7b-1t/"},{"id":"llama-3-1-tulu-3-8b","name":"Llama-3.1-Tulu-3-8B","hf":"allenai/Llama-3.1-Tulu-3-8B","org":"allenai","family":"olmo","series":"Llama-3.1-Tulu-3","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-11-20","updated":"2025-02-13","gated":false,"params":{"total":8.03,"active":null,"src":"safetensors","q":null,"stTotal":8.03},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":16.06,"t":19.2},"fp8":{"w":8.53,"t":11},"q4":{"w":4.87,"t":6.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.06,"native":"BF16","license":{"id":"llama3.1","name":"Llama 3.1 Community","link":null,"cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Llama-3.1-Tulu-3-8B","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Llama-3.1-Tulu-3-8B","u":"https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B"},{"t":"config.json","u":"https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-llama-3-1-tulu-3-8b"},{"id":"llama-3-1-tulu-3-405b","name":"Llama-3.1-Tulu-3-405B","hf":"allenai/Llama-3.1-Tulu-3-405B","org":"allenai","family":"olmo","series":"Llama-3.1-Tulu-3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-01-09","updated":"2025-02-10","gated":false,"params":{"total":405.854,"active":null,"src":"safetensors","q":null,"stTotal":405.854},"moe":false,"ctx":131072,"arch":{"L":126,"attn":126,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":4.23,"32768":16.91,"131072":67.65},"mem":{"bf16":{"w":811.71,"t":897.6},"fp8":{"w":431.22,"t":479.1},"q4":{"w":246.05,"t":275.4}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":811.71,"native":"BF16","license":{"id":"llama3.1","name":"Llama 3.1 Community","link":null,"cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Llama-3.1-Tulu-3-405B","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Llama-3.1-Tulu-3-405B","u":"https://huggingface.co/allenai/Llama-3.1-Tulu-3-405B"},{"t":"config.json","u":"https://huggingface.co/allenai/Llama-3.1-Tulu-3-405B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/llama-3-1-tulu-3-405b/"},{"id":"molmo-72b-0924","name":"Molmo-72B-0924","hf":"allenai/Molmo-72B-0924","org":"allenai","family":"olmo","series":"Molmo","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-09-25","updated":"2025-10-09","gated":false,"params":{"total":73.308,"active":null,"src":"safetensors","q":null,"stTotal":73.308},"moe":false,"ctx":4096,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68},"mem":{"bf16":{"w":146.62,"t":164.5},"fp8":{"w":77.89,"t":88.9},"q4":{"w":44.44,"t":52.1}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":293.23,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Molmo-72B-0924","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Molmo-72B-0924","u":"https://huggingface.co/allenai/Molmo-72B-0924"},{"t":"config.json","u":"https://huggingface.co/allenai/Molmo-72B-0924/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-molmo-72b-0924"},{"id":"molmo-7b-d-0924","name":"Molmo-7B-D-0924","hf":"allenai/Molmo-7B-D-0924","org":"allenai","family":"olmo","series":"Molmo-D","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-09-25","updated":"2025-12-15","gated":false,"params":{"total":8.021,"active":null,"src":"safetensors","q":null,"stTotal":8.021},"moe":false,"ctx":4096,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47},"mem":{"bf16":{"w":16.04,"t":18.6},"fp8":{"w":8.52,"t":10.3},"q4":{"w":4.86,"t":6.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":32.08,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Molmo-7B-D-0924","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Molmo-7B-D-0924","u":"https://huggingface.co/allenai/Molmo-7B-D-0924"},{"t":"config.json","u":"https://huggingface.co/allenai/Molmo-7B-D-0924/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-molmo-7b-d-0924"},{"id":"molmo-7b-o-0924","name":"Molmo-7B-O-0924","hf":"allenai/Molmo-7B-O-0924","org":"allenai","family":"olmo","series":"Molmo-O","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-09-25","updated":"2025-10-09","gated":false,"params":{"total":7.665,"active":null,"src":"safetensors","q":null,"stTotal":7.665},"moe":false,"ctx":4096,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":4.29},"mem":{"bf16":{"w":15.33,"t":21.7},"fp8":{"w":8.14,"t":13.7},"q4":{"w":4.65,"t":9.9}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac24"}},"disk":30.66,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Molmo-7B-O-0924","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Molmo-7B-O-0924","u":"https://huggingface.co/allenai/Molmo-7B-O-0924"},{"t":"config.json","u":"https://huggingface.co/allenai/Molmo-7B-O-0924/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-molmo-7b-o-0924"},{"id":"molmo2-4b","name":"Molmo2-4B","hf":"allenai/Molmo2-4B","org":"allenai","family":"olmo","series":"Molmo2","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-12-14","updated":"2026-01-23","gated":false,"params":{"total":4.851,"active":null,"src":"safetensors","q":null,"stTotal":4.851},"moe":false,"ctx":36864,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":9.7,"t":12.4},"fp8":{"w":5.15,"t":7.4},"q4":{"w":2.94,"t":4.9}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":19.4,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Molmo2-4B","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Molmo2-4B","u":"https://huggingface.co/allenai/Molmo2-4B"},{"t":"config.json","u":"https://huggingface.co/allenai/Molmo2-4B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-molmo2-4b"},{"id":"molmo2-8b","name":"Molmo2-8B","hf":"allenai/Molmo2-8B","org":"allenai","family":"olmo","series":"Molmo2","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-12-14","updated":"2026-01-23","gated":false,"params":{"total":8.662,"active":null,"src":"safetensors","q":null,"stTotal":8.662},"moe":false,"ctx":36864,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":17.32,"t":20.8},"fp8":{"w":9.2,"t":11.8},"q4":{"w":5.25,"t":7.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":34.65,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Molmo2-8B","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Molmo2-8B","u":"https://huggingface.co/allenai/Molmo2-8B"},{"t":"config.json","u":"https://huggingface.co/allenai/Molmo2-8B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-molmo2-8b"},{"id":"molmo2-er","name":"Molmo2-ER","hf":"allenai/Molmo2-ER","org":"allenai","family":"olmo","series":"Molmo2-ER","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-05-04","updated":"2026-05-21","gated":false,"params":{"total":4.851,"active":null,"src":"safetensors","q":null,"stTotal":4.851},"moe":false,"ctx":16384,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21},"mem":{"bf16":{"w":9.7,"t":12.4},"fp8":{"w":5.15,"t":7.4},"q4":{"w":2.94,"t":4.9}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":19.4,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Molmo2-ER","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Molmo2-ER","u":"https://huggingface.co/allenai/Molmo2-ER"},{"t":"config.json","u":"https://huggingface.co/allenai/Molmo2-ER/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-molmo2-er"},{"id":"molmo2-o-7b","name":"Molmo2-O-7B","hf":"allenai/Molmo2-O-7B","org":"allenai","family":"olmo","series":"Molmo2-O","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-12-14","updated":"2026-01-23","gated":false,"params":{"total":7.761,"active":null,"src":"safetensors","q":null,"stTotal":7.761},"moe":false,"ctx":65536,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":4.29,"32768":17.18},"mem":{"bf16":{"w":15.52,"t":21.9},"fp8":{"w":8.25,"t":13.9},"q4":{"w":4.71,"t":10}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac24"}},"disk":31.04,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Molmo2-O-7B","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Molmo2-O-7B","u":"https://huggingface.co/allenai/Molmo2-O-7B"},{"t":"config.json","u":"https://huggingface.co/allenai/Molmo2-O-7B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-molmo2-o-7b"},{"id":"molmoe-1b-0924","name":"MolmoE-1B-0924","hf":"allenai/MolmoE-1B-0924","org":"allenai","family":"olmo","series":"MolmoE","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-09-24","updated":"2025-04-24","gated":false,"params":{"total":7.2,"active":1.5,"src":"card","q":"1.5B active and 7.2B total parameters","stTotal":null},"moe":true,"ctx":32768,"arch":{"L":16,"attn":null,"slide":null,"win":null,"kvElems":null,"kvMethod":null,"exotic":[]},"kv":null,"mem":{"bf16":{"w":14.4,"t":16.3},"fp8":{"w":7.65,"t":8.9},"q4":{"w":4.37,"t":5.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":28.89,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/MolmoE-1B-0924","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/MolmoE-1B-0924","u":"https://huggingface.co/allenai/MolmoE-1B-0924"},{"t":"config.json","u":"https://huggingface.co/allenai/MolmoE-1B-0924/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-molmoe-1b-0924"},{"id":"molmopoint-8b","name":"MolmoPoint-8B","hf":"allenai/MolmoPoint-8B","org":"allenai","family":"olmo","series":"MolmoPoint","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-03-16","updated":"2026-03-18","gated":false,"params":{"total":8.678,"active":null,"src":"safetensors","q":null,"stTotal":8.678},"moe":false,"ctx":37376,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":17.36,"t":20.8},"fp8":{"w":9.22,"t":11.9},"q4":{"w":5.26,"t":7.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":34.71,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/MolmoPoint-8B","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/MolmoPoint-8B","u":"https://huggingface.co/allenai/MolmoPoint-8B"},{"t":"config.json","u":"https://huggingface.co/allenai/MolmoPoint-8B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-molmopoint-8b"},{"id":"molmoweb-4b","name":"MolmoWeb-4B","hf":"allenai/MolmoWeb-4B","org":"allenai","family":"olmo","series":"MolmoWeb","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-03-20","updated":"2026-04-10","gated":false,"params":{"total":4.851,"active":null,"src":"safetensors","q":null,"stTotal":4.851},"moe":false,"ctx":10240,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21},"mem":{"bf16":{"w":9.7,"t":12.4},"fp8":{"w":5.15,"t":7.4},"q4":{"w":2.94,"t":4.9}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":19.4,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/MolmoWeb-4B","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/MolmoWeb-4B","u":"https://huggingface.co/allenai/MolmoWeb-4B"},{"t":"config.json","u":"https://huggingface.co/allenai/MolmoWeb-4B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-molmoweb-4b"},{"id":"olmo-1b-0724-hf","name":"OLMo-1B-0724-hf","hf":"allenai/OLMo-1B-0724-hf","org":"allenai","family":"olmo","series":"OLMo","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-06-15","updated":"2024-08-05","gated":false,"params":{"total":1.28,"active":null,"src":"safetensors","q":null,"stTotal":1.28},"moe":false,"ctx":4096,"arch":{"L":16,"attn":16,"slide":0,"win":null,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07},"mem":{"bf16":{"w":2.56,"t":4.4},"fp8":{"w":1.36,"t":3.1},"q4":{"w":0.78,"t":2.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.12,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/OLMo-1B-0724-hf","kind":"HF-transformers"}],"sources":[{"t":"Hugging Face · allenai/OLMo-1B-0724-hf","u":"https://huggingface.co/allenai/OLMo-1B-0724-hf"},{"t":"config.json","u":"https://huggingface.co/allenai/OLMo-1B-0724-hf/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-1b-0724-hf"},{"id":"olmo-7b-0724-hf","name":"OLMo-7B-0724-hf","hf":"allenai/OLMo-7B-0724-hf","org":"allenai","family":"olmo","series":"OLMo","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-07-12","updated":"2024-07-16","gated":false,"params":{"total":6.888,"active":null,"src":"safetensors","q":null,"stTotal":6.888},"moe":false,"ctx":4096,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":4.29},"mem":{"bf16":{"w":13.78,"t":19.9},"fp8":{"w":7.32,"t":12.8},"q4":{"w":4.18,"t":9.4}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":27.55,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/OLMo-7B-0724-hf","kind":"HF-transformers"},{"id":"allenai/OLMo-7B-0724-Instruct-hf","kind":"Instruct/HF-transformers"}],"sources":[{"t":"Hugging Face · allenai/OLMo-7B-0724-hf","u":"https://huggingface.co/allenai/OLMo-7B-0724-hf"},{"t":"config.json","u":"https://huggingface.co/allenai/OLMo-7B-0724-hf/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-7b-0724-hf"},{"id":"olmo-2-0425-1b","name":"OLMo-2-0425-1B","hf":"allenai/OLMo-2-0425-1B","org":"allenai","family":"olmo","series":"OLMo-2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-17","updated":"2025-05-28","gated":false,"params":{"total":1.485,"active":null,"src":"safetensors","q":null,"stTotal":1.485},"moe":false,"ctx":4096,"arch":{"L":16,"attn":16,"slide":0,"win":null,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07},"mem":{"bf16":{"w":2.97,"t":4.8},"fp8":{"w":1.58,"t":3.3},"q4":{"w":0.9,"t":2.6}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.94,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"allenai/OLMo-2-0425-1B","kind":"main"},{"id":"allenai/OLMo-2-0425-1B-Instruct","kind":"Instruct"},{"id":"allenai/OLMo-2-0425-1B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"allenai/OLMo-2-0425-1B-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · allenai/OLMo-2-0425-1B","u":"https://huggingface.co/allenai/OLMo-2-0425-1B"},{"t":"config.json","u":"https://huggingface.co/allenai/OLMo-2-0425-1B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-2-0425-1b"},{"id":"olmo-2-1124-7b","name":"OLMo-2-1124-7B","hf":"allenai/OLMo-2-1124-7B","org":"allenai","family":"olmo","series":"OLMo-2","task":"llm","pipeline":null,"tags":[],"released":"2024-10-29","updated":"2025-01-06","gated":false,"params":{"total":7.299,"active":null,"src":"safetensors","q":null,"stTotal":7.299},"moe":false,"ctx":4096,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":4.29},"mem":{"bf16":{"w":14.6,"t":20.8},"fp8":{"w":7.76,"t":13.3},"q4":{"w":4.43,"t":9.7}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac24"}},"disk":29.19,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"allenai/OLMo-2-1124-7B","kind":"main"},{"id":"allenai/OLMo-2-1124-7B-Instruct","kind":"Instruct"},{"id":"allenai/OLMo-2-1124-7B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"allenai/OLMo-2-1124-7B-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · allenai/OLMo-2-1124-7B","u":"https://huggingface.co/allenai/OLMo-2-1124-7B"},{"t":"config.json","u":"https://huggingface.co/allenai/OLMo-2-1124-7B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-2-1124-7b"},{"id":"olmo-2-1124-13b","name":"OLMo-2-1124-13B","hf":"allenai/OLMo-2-1124-13B","org":"allenai","family":"olmo","series":"OLMo-2","task":"llm","pipeline":null,"tags":[],"released":"2024-11-19","updated":"2025-01-06","gated":false,"params":{"total":13.716,"active":null,"src":"safetensors","q":null,"stTotal":13.716},"moe":false,"ctx":4096,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":10240,"kvMethod":"gqa","exotic":[]},"kv":{"8192":6.71},"mem":{"bf16":{"w":27.43,"t":37.4},"fp8":{"w":14.57,"t":23.2},"q4":{"w":8.32,"t":16.4}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":54.86,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"allenai/OLMo-2-1124-13B","kind":"main"},{"id":"allenai/OLMo-2-1124-13B-Instruct","kind":"Instruct"},{"id":"allenai/OLMo-2-1124-13B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"allenai/OLMo-2-1124-13B-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · allenai/OLMo-2-1124-13B","u":"https://huggingface.co/allenai/OLMo-2-1124-13B"},{"t":"config.json","u":"https://huggingface.co/allenai/OLMo-2-1124-13B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-2-1124-13b"},{"id":"olmo-2-0325-32b-instruct","name":"OLMo-2-0325-32B-Instruct","hf":"allenai/OLMo-2-0325-32B-Instruct","org":"allenai","family":"olmo","series":"OLMo-2","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-03-12","updated":"2025-03-14","gated":false,"params":{"total":32.234,"active":null,"src":"safetensors","q":null,"stTotal":32.234},"moe":false,"ctx":4096,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15},"mem":{"bf16":{"w":64.47,"t":73.6},"fp8":{"w":34.25,"t":40.3},"q4":{"w":19.54,"t":24.1}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":64.47,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"allenai/OLMo-2-0325-32B-Instruct","kind":"Instruct"},{"id":"allenai/OLMo-2-0325-32B","kind":"main"},{"id":"allenai/OLMo-2-0325-32B-Instruct-GGUF","kind":"Instruct/GGUF"}],"sources":[{"t":"Hugging Face · allenai/OLMo-2-0325-32B-Instruct","u":"https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct"},{"t":"config.json","u":"https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-2-0325-32b-instruct"},{"id":"olmoe-1b-7b-0924","name":"OLMoE-1B-7B-0924","hf":"allenai/OLMoE-1B-7B-0924","org":"allenai","family":"olmo","series":"OLMoE","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-07-20","updated":"2024-10-19","gated":false,"params":{"total":6.919,"active":null,"src":"safetensors","q":null,"stTotal":6.919},"moe":true,"ctx":4096,"arch":{"L":16,"attn":16,"slide":0,"win":null,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07},"mem":{"bf16":{"w":13.84,"t":16.8},"fp8":{"w":7.35,"t":9.7},"q4":{"w":4.19,"t":6.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":13.84,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"allenai/OLMoE-1B-7B-0924","kind":"main"},{"id":"allenai/OLMoE-1B-7B-0924-Instruct","kind":"Instruct"},{"id":"allenai/OLMoE-1B-7B-0924-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"allenai/OLMoE-1B-7B-0924-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · allenai/OLMoE-1B-7B-0924","u":"https://huggingface.co/allenai/OLMoE-1B-7B-0924"},{"t":"config.json","u":"https://huggingface.co/allenai/OLMoE-1B-7B-0924/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmoe-1b-7b-0924"},{"id":"olmoe-1b-7b-0125-instruct","name":"OLMoE-1B-7B-0125-Instruct","hf":"allenai/OLMoE-1B-7B-0125-Instruct","org":"allenai","family":"olmo","series":"OLMoE","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-01-27","updated":"2025-02-04","gated":false,"params":{"total":6.919,"active":null,"src":"safetensors","q":null,"stTotal":6.919},"moe":true,"ctx":4096,"arch":{"L":16,"attn":16,"slide":0,"win":null,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07},"mem":{"bf16":{"w":13.84,"t":16.8},"fp8":{"w":7.35,"t":9.7},"q4":{"w":4.19,"t":6.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":13.84,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"allenai/OLMoE-1B-7B-0125-Instruct","kind":"Instruct"},{"id":"allenai/OLMoE-1B-7B-0125","kind":"main"},{"id":"allenai/OLMoE-1B-7B-0125-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"allenai/OLMoE-1B-7B-0125-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · allenai/OLMoE-1B-7B-0125-Instruct","u":"https://huggingface.co/allenai/OLMoE-1B-7B-0125-Instruct"},{"t":"config.json","u":"https://huggingface.co/allenai/OLMoE-1B-7B-0125-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmoe-1b-7b-0125-instruct"},{"id":"olmo-3-7b-instruct","name":"Olmo-3-7B-Instruct","hf":"allenai/Olmo-3-7B-Instruct","org":"allenai","family":"olmo","series":"Olmo-3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-11-19","updated":"2026-06-25","gated":false,"params":{"total":7.298,"active":null,"src":"safetensors","q":null,"stTotal":7.298},"moe":false,"ctx":65536,"arch":{"L":32,"attn":8,"slide":24,"win":4096,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":5.91},"mem":{"bf16":{"w":14.6,"t":19.2},"fp8":{"w":7.75,"t":11.7},"q4":{"w":4.42,"t":8}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":14.6,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"olmo-3:7b","url":"https://ollama.com/library/olmo-3"}],"variants":[{"id":"allenai/Olmo-3-7B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · allenai/Olmo-3-7B-Instruct","u":"https://huggingface.co/allenai/Olmo-3-7B-Instruct"},{"t":"config.json","u":"https://huggingface.co/allenai/Olmo-3-7B-Instruct/blob/main/config.json"},{"t":"Ollama library · olmo-3","u":"https://ollama.com/library/olmo-3"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-3-7b-instruct"},{"id":"olmo-3-1025-7b","name":"Olmo-3-1025-7B","hf":"allenai/Olmo-3-1025-7B","org":"allenai","family":"olmo","series":"Olmo-3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-12","updated":"2026-04-21","gated":false,"params":{"total":7.298,"active":null,"src":"safetensors","q":null,"stTotal":7.298},"moe":false,"ctx":65536,"arch":{"L":32,"attn":8,"slide":24,"win":4096,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":5.91},"mem":{"bf16":{"w":14.6,"t":19.2},"fp8":{"w":7.75,"t":11.7},"q4":{"w":4.42,"t":8}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":14.6,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Olmo-3-1025-7B","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Olmo-3-1025-7B","u":"https://huggingface.co/allenai/Olmo-3-1025-7B"},{"t":"config.json","u":"https://huggingface.co/allenai/Olmo-3-1025-7B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-3-1025-7b"},{"id":"olmo-3-1125-32b","name":"Olmo-3-1125-32B","hf":"allenai/Olmo-3-1125-32B","org":"allenai","family":"olmo","series":"Olmo-3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-11-04","updated":"2025-12-03","gated":false,"params":{"total":32.234,"active":null,"src":"safetensors","q":null,"stTotal":32.234},"moe":false,"ctx":65536,"arch":{"L":64,"attn":16,"slide":48,"win":4096,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":2.95},"mem":{"bf16":{"w":64.47,"t":72.8},"fp8":{"w":34.25,"t":39.5},"q4":{"w":19.54,"t":23.3}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":64.47,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Olmo-3-1125-32B","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Olmo-3-1125-32B","u":"https://huggingface.co/allenai/Olmo-3-1125-32B"},{"t":"config.json","u":"https://huggingface.co/allenai/Olmo-3-1125-32B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-3-1125-32b"},{"id":"olmo-3-7b-think","name":"Olmo-3-7B-Think","hf":"allenai/Olmo-3-7B-Think","org":"allenai","family":"olmo","series":"Olmo-3-Think","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-11-18","updated":"2026-06-25","gated":false,"params":{"total":7.298,"active":null,"src":"safetensors","q":null,"stTotal":7.298},"moe":false,"ctx":65536,"arch":{"L":32,"attn":8,"slide":24,"win":4096,"kvElems":8192,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":5.91},"mem":{"bf16":{"w":14.6,"t":19.2},"fp8":{"w":7.75,"t":11.7},"q4":{"w":4.42,"t":8}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":14.6,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Olmo-3-7B-Think","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Olmo-3-7B-Think","u":"https://huggingface.co/allenai/Olmo-3-7B-Think"},{"t":"config.json","u":"https://huggingface.co/allenai/Olmo-3-7B-Think/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-3-7b-think"},{"id":"olmo-3-32b-think","name":"Olmo-3-32B-Think","hf":"allenai/Olmo-3-32B-Think","org":"allenai","family":"olmo","series":"Olmo-3-Think","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-11-19","updated":"2026-06-25","gated":false,"params":{"total":32.234,"active":null,"src":"safetensors","q":null,"stTotal":32.234},"moe":false,"ctx":65536,"arch":{"L":64,"attn":16,"slide":48,"win":4096,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":2.95},"mem":{"bf16":{"w":64.47,"t":72.8},"fp8":{"w":34.25,"t":39.5},"q4":{"w":19.54,"t":23.3}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":64.47,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Olmo-3-32B-Think","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Olmo-3-32B-Think","u":"https://huggingface.co/allenai/Olmo-3-32B-Think"},{"t":"config.json","u":"https://huggingface.co/allenai/Olmo-3-32B-Think/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-3-32b-think"},{"id":"olmo-3-1-32b-instruct","name":"Olmo-3.1-32B-Instruct","hf":"allenai/Olmo-3.1-32B-Instruct","org":"allenai","family":"olmo","series":"Olmo-3.1","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-12-10","updated":"2026-01-05","gated":false,"params":{"total":32.234,"active":null,"src":"safetensors","q":null,"stTotal":32.234},"moe":false,"ctx":65536,"arch":{"L":64,"attn":16,"slide":48,"win":4096,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":2.95},"mem":{"bf16":{"w":64.47,"t":72.8},"fp8":{"w":34.25,"t":39.5},"q4":{"w":19.54,"t":23.3}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":64.47,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"olmo-3.1:32b","url":"https://ollama.com/library/olmo-3.1"}],"variants":[{"id":"allenai/Olmo-3.1-32B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · allenai/Olmo-3.1-32B-Instruct","u":"https://huggingface.co/allenai/Olmo-3.1-32B-Instruct"},{"t":"config.json","u":"https://huggingface.co/allenai/Olmo-3.1-32B-Instruct/blob/main/config.json"},{"t":"Ollama library · olmo-3.1","u":"https://ollama.com/library/olmo-3.1"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-3-1-32b-instruct"},{"id":"olmo-3-1-32b-think","name":"Olmo-3.1-32B-Think","hf":"allenai/Olmo-3.1-32B-Think","org":"allenai","family":"olmo","series":"Olmo-3.1-Think","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-12-10","updated":"2026-10-13","gated":false,"params":{"total":32.234,"active":null,"src":"safetensors","q":null,"stTotal":32.234},"moe":false,"ctx":65536,"arch":{"L":64,"attn":16,"slide":48,"win":4096,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":2.95},"mem":{"bf16":{"w":64.47,"t":72.8},"fp8":{"w":34.25,"t":39.5},"q4":{"w":19.54,"t":23.3}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":64.47,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Olmo-3.1-32B-Think","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Olmo-3.1-32B-Think","u":"https://huggingface.co/allenai/Olmo-3.1-32B-Think"},{"t":"config.json","u":"https://huggingface.co/allenai/Olmo-3.1-32B-Think/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-3-1-32b-think"},{"id":"olmo-hybrid-7b","name":"Olmo-Hybrid-7B","hf":"allenai/Olmo-Hybrid-7B","org":"allenai","family":"olmo","series":"Olmo-Hybrid","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-01-28","updated":"2026-05-26","gated":false,"params":{"total":7.431,"active":null,"src":"safetensors","q":null,"stTotal":7.431},"moe":false,"ctx":65536,"arch":{"L":32,"attn":8,"slide":0,"win":null,"kvElems":7680,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":1.01,"32768":4.03},"mem":{"bf16":{"w":14.86,"t":17.9},"fp8":{"w":7.9,"t":10.2},"q4":{"w":4.51,"t":6.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":14.86,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/Olmo-Hybrid-7B","kind":"main"}],"sources":[{"t":"Hugging Face · allenai/Olmo-Hybrid-7B","u":"https://huggingface.co/allenai/Olmo-Hybrid-7B"},{"t":"config.json","u":"https://huggingface.co/allenai/Olmo-Hybrid-7B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmo-hybrid-7b"},{"id":"olmocr-2-7b-1025","name":"olmOCR-2-7B-1025","hf":"allenai/olmOCR-2-7B-1025","org":"allenai","family":"olmo","series":"olmOCR-2","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2025-10-06","updated":"2025-10-22","gated":false,"params":{"total":8.292,"active":null,"src":"safetensors","q":null,"stTotal":8.292},"moe":false,"ctx":128000,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":16.58,"t":19.2},"fp8":{"w":8.81,"t":10.7},"q4":{"w":5.03,"t":6.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.58,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"allenai/olmOCR-2-7B-1025","kind":"main"},{"id":"allenai/olmOCR-2-7B-1025-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · allenai/olmOCR-2-7B-1025","u":"https://huggingface.co/allenai/olmOCR-2-7B-1025"},{"t":"config.json","u":"https://huggingface.co/allenai/olmOCR-2-7B-1025/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmocr-2-7b-1025"},{"id":"olmocr-7b-0225-preview","name":"olmOCR-7B-0225-preview","hf":"allenai/olmOCR-7B-0225-preview","org":"allenai","family":"olmo","series":"olmOCR-preview","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2025-01-15","updated":"2025-08-19","gated":false,"params":{"total":8.291,"active":null,"src":"safetensors","q":null,"stTotal":8.291},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":16.58,"t":19.2},"fp8":{"w":8.81,"t":10.7},"q4":{"w":5.03,"t":6.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.58,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"allenai/olmOCR-7B-0225-preview","kind":"main"},{"id":"allenai/olmOCR-7B-0225-preview-FP8","kind":"FP8"},{"id":"allenai/olmOCR-7B-0225-preview-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · allenai/olmOCR-7B-0225-preview","u":"https://huggingface.co/allenai/olmOCR-7B-0225-preview"},{"t":"config.json","u":"https://huggingface.co/allenai/olmOCR-7B-0225-preview/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/olmo/#m-olmocr-7b-0225-preview"},{"id":"phi-3-medium-128k-instruct","name":"Phi-3-medium-128k-instruct","hf":"microsoft/Phi-3-medium-128k-instruct","org":"microsoft","family":"phi","series":"Phi-3-medium-128k","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-07","updated":"2025-12-10","gated":false,"params":{"total":13.96,"active":null,"src":"safetensors","q":null,"stTotal":13.96},"moe":false,"ctx":131072,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2560,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.68,"32768":6.71,"131072":26.84},"mem":{"bf16":{"w":27.92,"t":32.9},"fp8":{"w":14.83,"t":18.5},"q4":{"w":8.46,"t":11.5}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":27.92,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-3-medium-128k-instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · microsoft/Phi-3-medium-128k-instruct","u":"https://huggingface.co/microsoft/Phi-3-medium-128k-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-3-medium-128k-instruct"},{"id":"phi-3-medium-4k-instruct","name":"Phi-3-medium-4k-instruct","hf":"microsoft/Phi-3-medium-4k-instruct","org":"microsoft","family":"phi","series":"Phi-3-medium-4k","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-07","updated":"2025-12-10","gated":false,"params":{"total":13.96,"active":null,"src":"safetensors","q":null,"stTotal":13.96},"moe":false,"ctx":4096,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2560,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.68},"mem":{"bf16":{"w":27.92,"t":32.9},"fp8":{"w":14.83,"t":18.5},"q4":{"w":8.46,"t":11.5}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":27.92,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-3-medium-4k-instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · microsoft/Phi-3-medium-4k-instruct","u":"https://huggingface.co/microsoft/Phi-3-medium-4k-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/resolve/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-3-medium-4k-instruct"},{"id":"phi-3-small-128k-instruct","name":"Phi-3-small-128k-instruct","hf":"microsoft/Phi-3-small-128k-instruct","org":"microsoft","family":"phi","series":"Phi-3-small-128k","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-07","updated":"2025-12-10","gated":false,"params":{"total":7.392,"active":null,"src":"safetensors","q":null,"stTotal":7.392},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":14.78,"t":17.8},"fp8":{"w":7.85,"t":10.2},"q4":{"w":4.48,"t":6.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":14.78,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-3-small-128k-instruct/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-3-small-128k-instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · microsoft/Phi-3-small-128k-instruct","u":"https://huggingface.co/microsoft/Phi-3-small-128k-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-3-small-128k-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-3-small-128k-instruct/resolve/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-3-small-128k-instruct"},{"id":"phi-3-small-8k-instruct","name":"Phi-3-small-8k-instruct","hf":"microsoft/Phi-3-small-8k-instruct","org":"microsoft","family":"phi","series":"Phi-3-small-8k","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-07","updated":"2025-12-10","gated":false,"params":{"total":7.392,"active":null,"src":"safetensors","q":null,"stTotal":7.392},"moe":false,"ctx":8192,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07},"mem":{"bf16":{"w":14.78,"t":17.8},"fp8":{"w":7.85,"t":10.2},"q4":{"w":4.48,"t":6.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":14.78,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-3-small-8k-instruct/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-3-small-8k-instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · microsoft/Phi-3-small-8k-instruct","u":"https://huggingface.co/microsoft/Phi-3-small-8k-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-3-small-8k-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-3-small-8k-instruct/resolve/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-3-small-8k-instruct"},{"id":"phi-3-vision-128k-instruct","name":"Phi-3-vision-128k-instruct","hf":"microsoft/Phi-3-vision-128k-instruct","org":"microsoft","family":"phi","series":"Phi-3-vision-128k","task":"vlm","pipeline":"text-generation","tags":[],"released":"2024-05-19","updated":"2025-12-10","gated":false,"params":{"total":4.147,"active":null,"src":"safetensors","q":null,"stTotal":4.147},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":6144,"kvMethod":"gqa","exotic":[]},"kv":{"8192":3.22,"32768":12.88,"131072":51.54},"mem":{"bf16":{"w":8.29,"t":12.8},"fp8":{"w":4.41,"t":8.6},"q4":{"w":2.51,"t":6.5}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.29,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-3-vision-128k-instruct/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-3-vision-128k-instruct","kind":"Instruct"},{"id":"microsoft/Phi-3-vision-128k-instruct-onnx","kind":"Instruct/ONNX"}],"sources":[{"t":"Hugging Face · microsoft/Phi-3-vision-128k-instruct","u":"https://huggingface.co/microsoft/Phi-3-vision-128k-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-3-vision-128k-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-3-vision-128k-instruct/resolve/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-3-vision-128k-instruct"},{"id":"phi-3-5-moe-instruct","name":"Phi-3.5-MoE-instruct","hf":"microsoft/Phi-3.5-MoE-instruct","org":"microsoft","family":"phi","series":"Phi-3.5-MoE","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-08-17","updated":"2025-12-10","gated":false,"params":{"total":41.9,"active":6.6,"src":"card","q":"16x3.8B parameters with 6.6B active parameters","stTotal":41.873},"moe":true,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":83.8,"t":93.8},"fp8":{"w":44.52,"t":50.5},"q4":{"w":25.4,"t":29.5}},"fits":{"bf16":{"gpu":"h200","mac":"mac256"},"fp8":{"gpu":"2x5090","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac64"}},"disk":83.75,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-3.5-MoE-instruct/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-3.5-MoE-instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · microsoft/Phi-3.5-MoE-instruct","u":"https://huggingface.co/microsoft/Phi-3.5-MoE-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-3.5-MoE-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-3.5-MoE-instruct/resolve/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-3-5-moe-instruct"},{"id":"phi-3-5-mini-instruct","name":"Phi-3.5-mini-instruct","hf":"microsoft/Phi-3.5-mini-instruct","org":"microsoft","family":"phi","series":"Phi-3.5-mini","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-08-16","updated":"2025-12-10","gated":false,"params":{"total":3.821,"active":null,"src":"safetensors","q":null,"stTotal":3.821},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":6144,"kvMethod":"gqa","exotic":[]},"kv":{"8192":3.22,"32768":12.88,"131072":51.54},"mem":{"bf16":{"w":7.64,"t":12.1},"fp8":{"w":4.06,"t":8.2},"q4":{"w":2.32,"t":6.3}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.64,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-3.5-mini-instruct/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-3.5-mini-instruct","kind":"Instruct"},{"id":"microsoft/Phi-3.5-mini-instruct-onnx","kind":"Instruct/ONNX"}],"sources":[{"t":"Hugging Face · microsoft/Phi-3.5-mini-instruct","u":"https://huggingface.co/microsoft/Phi-3.5-mini-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-3.5-mini-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-3.5-mini-instruct/resolve/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-3-5-mini-instruct"},{"id":"phi-3-5-vision-instruct","name":"Phi-3.5-vision-instruct","hf":"microsoft/Phi-3.5-vision-instruct","org":"microsoft","family":"phi","series":"Phi-3.5-vision","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-08-16","updated":"2025-12-10","gated":false,"params":{"total":4.147,"active":null,"src":"safetensors","q":null,"stTotal":4.147},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":6144,"kvMethod":"gqa","exotic":[]},"kv":{"8192":3.22,"32768":12.88,"131072":51.54},"mem":{"bf16":{"w":8.29,"t":12.8},"fp8":{"w":4.41,"t":8.6},"q4":{"w":2.51,"t":6.5}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.29,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-3.5-vision-instruct/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-3.5-vision-instruct","kind":"Instruct"},{"id":"microsoft/Phi-3.5-vision-instruct-onnx","kind":"Instruct/ONNX"}],"sources":[{"t":"Hugging Face · microsoft/Phi-3.5-vision-instruct","u":"https://huggingface.co/microsoft/Phi-3.5-vision-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-3.5-vision-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-3.5-vision-instruct/resolve/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-3-5-vision-instruct"},{"id":"phi-4-mini-instruct","name":"Phi-4-mini-instruct","hf":"microsoft/Phi-4-mini-instruct","org":"microsoft","family":"phi","series":"Phi-4-mini","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-02-19","updated":"2025-12-10","gated":false,"params":{"total":3.836,"active":null,"src":"safetensors","q":null,"stTotal":3.836},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":7.67,"t":10},"fp8":{"w":4.08,"t":6.1},"q4":{"w":2.33,"t":4.1}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.67,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-4-mini-instruct/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"phi4-mini","url":"https://ollama.com/library/phi4-mini"}],"variants":[{"id":"microsoft/Phi-4-mini-instruct","kind":"Instruct"},{"id":"microsoft/Phi-4-mini-instruct-onnx","kind":"Instruct/ONNX"}],"sources":[{"t":"Hugging Face · microsoft/Phi-4-mini-instruct","u":"https://huggingface.co/microsoft/Phi-4-mini-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-4-mini-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-4-mini-instruct/resolve/main/LICENSE"},{"t":"Ollama library · phi4-mini","u":"https://ollama.com/library/phi4-mini"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-4-mini-instruct"},{"id":"phi-4-mini-flash-reasoning","name":"Phi-4-mini-flash-reasoning","hf":"microsoft/Phi-4-mini-flash-reasoning","org":"microsoft","family":"phi","series":"Phi-4-mini-flash-reasoning","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-06-19","updated":"2025-12-10","gated":false,"params":{"total":3.853,"active":null,"src":"safetensors","q":null,"stTotal":3.853},"moe":false,"ctx":262144,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2560,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37,"131072":21.47},"mem":{"bf16":{"w":7.71,"t":10.3},"fp8":{"w":4.09,"t":6.3},"q4":{"w":2.34,"t":4.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.71,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-4-mini-flash-reasoning/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-4-mini-flash-reasoning","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/Phi-4-mini-flash-reasoning","u":"https://huggingface.co/microsoft/Phi-4-mini-flash-reasoning"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-4-mini-flash-reasoning/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-4-mini-flash-reasoning/resolve/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-4-mini-flash-reasoning"},{"id":"phi-4-mini-reasoning","name":"Phi-4-mini-reasoning","hf":"microsoft/Phi-4-mini-reasoning","org":"microsoft","family":"phi","series":"Phi-4-mini-reasoning","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-04-29","updated":"2025-12-10","gated":false,"params":{"total":3.836,"active":null,"src":"safetensors","q":null,"stTotal":3.836},"moe":false,"ctx":131072,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29,"131072":17.18},"mem":{"bf16":{"w":7.67,"t":10},"fp8":{"w":4.08,"t":6.1},"q4":{"w":2.33,"t":4.1}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.67,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-4-mini-instruct-reasoning/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"phi4-mini-reasoning","url":"https://ollama.com/library/phi4-mini-reasoning"}],"variants":[{"id":"microsoft/Phi-4-mini-reasoning","kind":"main"},{"id":"microsoft/Phi-4-mini-reasoning-onnx","kind":"ONNX"}],"sources":[{"t":"Hugging Face · microsoft/Phi-4-mini-reasoning","u":"https://huggingface.co/microsoft/Phi-4-mini-reasoning"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-4-mini-reasoning/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-4-mini-instruct-reasoning/resolve/main/LICENSE"},{"t":"Ollama library · phi4-mini-reasoning","u":"https://ollama.com/library/phi4-mini-reasoning"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-4-mini-reasoning"},{"id":"phi-4-multimodal-instruct","name":"Phi-4-multimodal-instruct","hf":"microsoft/Phi-4-multimodal-instruct","org":"microsoft","family":"phi","series":"Phi-4-multimodal","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2025-02-24","updated":"2025-12-10","gated":false,"params":{"total":5.574,"active":null,"src":"safetensors","q":null,"stTotal":5.574},"moe":false,"ctx":131072,"arch":null,"kv":null,"mem":{"bf16":{"w":11.15,"t":12.8},"fp8":{"w":5.92,"t":7},"q4":{"w":3.38,"t":4.2}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":11.15,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-4-multimodal-instruct","kind":"Instruct"},{"id":"microsoft/Phi-4-multimodal-instruct-onnx","kind":"Instruct/ONNX"}],"sources":[{"t":"Hugging Face · microsoft/Phi-4-multimodal-instruct","u":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct/resolve/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-4-multimodal-instruct"},{"id":"phi-4-reasoning","name":"Phi-4-reasoning","hf":"microsoft/Phi-4-reasoning","org":"microsoft","family":"phi","series":"Phi-4-reasoning","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-04-09","updated":"2025-11-24","gated":false,"params":{"total":14.66,"active":null,"src":"safetensors","q":null,"stTotal":14.66},"moe":false,"ctx":32768,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2560,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.68,"32768":6.71},"mem":{"bf16":{"w":29.32,"t":34.4},"fp8":{"w":15.58,"t":19.3},"q4":{"w":8.89,"t":12}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":29.32,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-4-reasoning/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"phi4-reasoning","url":"https://ollama.com/library/phi4-reasoning"}],"variants":[{"id":"microsoft/Phi-4-reasoning","kind":"main"},{"id":"microsoft/Phi-4-reasoning-onnx","kind":"ONNX"}],"sources":[{"t":"Hugging Face · microsoft/Phi-4-reasoning","u":"https://huggingface.co/microsoft/Phi-4-reasoning"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-4-reasoning/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-4-reasoning/resolve/main/LICENSE"},{"t":"Ollama library · phi4-reasoning","u":"https://ollama.com/library/phi4-reasoning"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-4-reasoning"},{"id":"phi-4-reasoning-plus","name":"Phi-4-reasoning-plus","hf":"microsoft/Phi-4-reasoning-plus","org":"microsoft","family":"phi","series":"Phi-4-reasoning-plus","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-04-17","updated":"2025-11-24","gated":false,"params":{"total":14.66,"active":null,"src":"safetensors","q":null,"stTotal":14.66},"moe":false,"ctx":32768,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2560,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.68,"32768":6.71},"mem":{"bf16":{"w":29.32,"t":34.4},"fp8":{"w":15.58,"t":19.3},"q4":{"w":8.89,"t":12}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":29.32,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-4-reasoning-plus/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-4-reasoning-plus","kind":"main"},{"id":"microsoft/Phi-4-reasoning-plus-onnx","kind":"ONNX"}],"sources":[{"t":"Hugging Face · microsoft/Phi-4-reasoning-plus","u":"https://huggingface.co/microsoft/Phi-4-reasoning-plus"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-4-reasoning-plus/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-4-reasoning-plus/resolve/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-4-reasoning-plus"},{"id":"phi-4-reasoning-vision-15b","name":"Phi-4-reasoning-vision-15B","hf":"microsoft/Phi-4-reasoning-vision-15B","org":"microsoft","family":"phi","series":"Phi-4-reasoning-vision","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2026-01-23","updated":"2026-08-31","gated":false,"params":{"total":15.12,"active":null,"src":"safetensors","q":null,"stTotal":15.12},"moe":false,"ctx":32768,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2560,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.68,"32768":6.71},"mem":{"bf16":{"w":30.24,"t":35.4},"fp8":{"w":16.06,"t":19.9},"q4":{"w":9.17,"t":12.3}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":30.24,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-4-reasoning-vision-15B","kind":"main"}],"sources":[{"t":"Hugging Face · microsoft/Phi-4-reasoning-vision-15B","u":"https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-4-reasoning-vision-15b"},{"id":"phi-mini-moe-instruct","name":"Phi-mini-MoE-instruct","hf":"microsoft/Phi-mini-MoE-instruct","org":"microsoft","family":"phi","series":"Phi-mini-MoE","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-23","updated":"2025-12-10","gated":false,"params":{"total":7.6,"active":2.4,"src":"card","q":"7.6B total parameters and 2.4B activated parameters","stTotal":7.648},"moe":true,"ctx":4096,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07},"mem":{"bf16":{"w":15.2,"t":18.3},"fp8":{"w":8.07,"t":10.5},"q4":{"w":4.61,"t":6.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.3,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-mini-MoE-instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-mini-MoE-instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · microsoft/Phi-mini-MoE-instruct","u":"https://huggingface.co/microsoft/Phi-mini-MoE-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-mini-MoE-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-mini-MoE-instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-mini-moe-instruct"},{"id":"phi-tiny-moe-instruct","name":"Phi-tiny-MoE-instruct","hf":"microsoft/Phi-tiny-MoE-instruct","org":"microsoft","family":"phi","series":"Phi-tiny-MoE","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-06-23","updated":"2025-12-10","gated":false,"params":{"total":3.8,"active":1.1,"src":"card","q":"3.8B total parameters and 1.1B activated parameters","stTotal":3.755},"moe":true,"ctx":4096,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54},"mem":{"bf16":{"w":7.6,"t":9.4},"fp8":{"w":4.04,"t":5.5},"q4":{"w":2.3,"t":3.6}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.51,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/Phi-tiny-MoE-instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"microsoft/Phi-tiny-MoE-instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · microsoft/Phi-tiny-MoE-instruct","u":"https://huggingface.co/microsoft/Phi-tiny-MoE-instruct"},{"t":"config.json","u":"https://huggingface.co/microsoft/Phi-tiny-MoE-instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/Phi-tiny-MoE-instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-tiny-moe-instruct"},{"id":"phi-4","name":"phi-4","hf":"microsoft/phi-4","org":"microsoft","family":"phi","series":"phi-4","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-12-11","updated":"2026-07-14","gated":false,"params":{"total":14.66,"active":null,"src":"safetensors","q":null,"stTotal":14.66},"moe":false,"ctx":16384,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2560,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.68},"mem":{"bf16":{"w":29.32,"t":34.4},"fp8":{"w":15.58,"t":19.3},"q4":{"w":8.89,"t":12}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":29.32,"native":"BF16","license":{"id":"mit","name":"MIT","link":"https://huggingface.co/microsoft/phi-4/resolve/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"phi4","url":"https://ollama.com/library/phi4"}],"variants":[{"id":"microsoft/phi-4","kind":"main"},{"id":"microsoft/phi-4-gguf","kind":"GGUF"},{"id":"microsoft/phi-4-onnx","kind":"ONNX"}],"sources":[{"t":"Hugging Face · microsoft/phi-4","u":"https://huggingface.co/microsoft/phi-4"},{"t":"config.json","u":"https://huggingface.co/microsoft/phi-4/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/microsoft/phi-4/resolve/main/LICENSE"},{"t":"Ollama library · phi4","u":"https://ollama.com/library/phi4"}],"page":"https://aimap.page/en/models/compute/open-models/family/phi/#m-phi-4"},{"id":"qvq-72b-preview","name":"QVQ-72B-Preview","hf":"Qwen/QVQ-72B-Preview","org":"Qwen","family":"qwen","series":"QVQ-Preview","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-12-24","updated":"2025-01-12","gated":false,"params":{"total":73.406,"active":null,"src":"safetensors","q":null,"stTotal":73.406},"moe":false,"ctx":128000,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74},"mem":{"bf16":{"w":146.81,"t":164.7},"fp8":{"w":77.99,"t":89},"q4":{"w":44.5,"t":52.1}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":146.81,"native":"BF16","license":{"id":"qwen","name":"qwen","link":"https://huggingface.co/Qwen/QVQ-72B-Preview/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/QVQ-72B-Preview","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/QVQ-72B-Preview","u":"https://huggingface.co/Qwen/QVQ-72B-Preview"},{"t":"config.json","u":"https://huggingface.co/Qwen/QVQ-72B-Preview/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/QVQ-72B-Preview/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qvq-72b-preview"},{"id":"qwq-32b","name":"QwQ-32B","hf":"Qwen/QwQ-32B","org":"Qwen","family":"qwen","series":"QwQ","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-03-05","updated":"2025-03-11","gated":false,"params":{"total":32.764,"active":null,"src":"safetensors","q":null,"stTotal":32.764},"moe":false,"ctx":40960,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59},"mem":{"bf16":{"w":65.53,"t":74.7},"fp8":{"w":34.81,"t":40.9},"q4":{"w":19.86,"t":24.5}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":65.53,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/QWQ-32B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwq:32b","url":"https://ollama.com/library/qwq"}],"variants":[{"id":"Qwen/QwQ-32B","kind":"main"},{"id":"Qwen/QwQ-32B-GGUF","kind":"GGUF"},{"id":"Qwen/QwQ-32B-AWQ","kind":"AWQ"}],"sources":[{"t":"Hugging Face · Qwen/QwQ-32B","u":"https://huggingface.co/Qwen/QwQ-32B"},{"t":"config.json","u":"https://huggingface.co/Qwen/QwQ-32B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/QWQ-32B/blob/main/LICENSE"},{"t":"Ollama library · qwq","u":"https://ollama.com/library/qwq"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwq-32b"},{"id":"qwq-32b-preview","name":"QwQ-32B-Preview","hf":"Qwen/QwQ-32B-Preview","org":"Qwen","family":"qwen","series":"QwQ-Preview","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2024-11-27","updated":"2025-01-12","gated":false,"params":{"total":32.764,"active":null,"src":"safetensors","q":null,"stTotal":32.764},"moe":false,"ctx":32768,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59},"mem":{"bf16":{"w":65.53,"t":74.7},"fp8":{"w":34.81,"t":40.9},"q4":{"w":19.86,"t":24.5}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":65.53,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/QwQ-32B-Preview/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/QwQ-32B-Preview","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/QwQ-32B-Preview","u":"https://huggingface.co/Qwen/QwQ-32B-Preview"},{"t":"config.json","u":"https://huggingface.co/Qwen/QwQ-32B-Preview/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/QwQ-32B-Preview/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwq-32b-preview"},{"id":"qwen-image","name":"Qwen-Image","hf":"Qwen/Qwen-Image","org":"Qwen","family":"qwen","series":"Qwen-Image","task":"image","pipeline":"text-to-image","tags":[],"released":"2025-08-02","updated":"2025-08-18","gated":false,"params":{"total":20.43,"active":null,"src":"safetensors","q":null,"stTotal":20.43},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":40.86,"t":45.4},"fp8":{"w":21.71,"t":24.4},"q4":{"w":12.39,"t":14.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":57.7,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen-Image/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"Qwen/Qwen-Image","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen-Image","u":"https://huggingface.co/Qwen/Qwen-Image"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen-Image/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen-image"},{"id":"qwen-image-2512","name":"Qwen-Image-2512","hf":"Qwen/Qwen-Image-2512","org":"Qwen","family":"qwen","series":"Qwen-Image","task":"image","pipeline":"text-to-image","tags":[],"released":"2025-12-30","updated":"2025-12-31","gated":false,"params":{"total":20.43,"active":null,"src":"safetensors","q":null,"stTotal":20.43},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":40.86,"t":45.4},"fp8":{"w":21.71,"t":24.4},"q4":{"w":12.39,"t":14.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":57.7,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"Qwen/Qwen-Image-2512","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen-Image-2512","u":"https://huggingface.co/Qwen/Qwen-Image-2512"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen-image-2512"},{"id":"qwen-image-2-1","name":"Qwen-Image-2.1","hf":"Qwen/Qwen-Image-2.1","org":"Qwen","family":"qwen","series":"Qwen-Image-2.1","task":"image","pipeline":"text-to-image","tags":[],"released":"2026-09-14","updated":"2026-09-30","gated":false,"params":{"total":7.115,"active":null,"src":"safetensors","q":null,"stTotal":7.115},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":14.23,"t":16.2},"fp8":{"w":7.56,"t":8.8},"q4":{"w":4.31,"t":5.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":33.12,"native":"BF16","license":{"id":"qwen-research","name":"qwen-research","link":"https://huggingface.co/Qwen/Qwen-Image-2.1/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"Qwen/Qwen-Image-2.1","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen-Image-2.1","u":"https://huggingface.co/Qwen/Qwen-Image-2.1"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen-Image-2.1/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/qwen-image-2-1/"},{"id":"qwen-image-2-1-turbo","name":"Qwen-Image-2.1-Turbo","hf":"Qwen/Qwen-Image-2.1-Turbo","org":"Qwen","family":"qwen","series":"Qwen-Image-2.1-Turbo","task":"image","pipeline":"text-to-image","tags":[],"released":"2026-10-09","updated":"2026-10-12","gated":false,"params":{"total":7.115,"active":null,"src":"safetensors","q":null,"stTotal":7.115},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":14.23,"t":16.2},"fp8":{"w":7.56,"t":8.8},"q4":{"w":4.31,"t":5.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":32.44,"native":"BF16","license":{"id":"qwen-research","name":"qwen-research","link":"https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"Qwen/Qwen-Image-2.1-Turbo","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen-Image-2.1-Turbo","u":"https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/qwen-image-2-1-turbo/"},{"id":"qwen-image-edit-2511","name":"Qwen-Image-Edit-2511","hf":"Qwen/Qwen-Image-Edit-2511","org":"Qwen","family":"qwen","series":"Qwen-Image-Edit","task":"image","pipeline":"image-to-image","tags":[],"released":"2025-12-17","updated":"2025-12-23","gated":false,"params":{"total":20.43,"active":null,"src":"safetensors","q":null,"stTotal":20.43},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":40.86,"t":45.4},"fp8":{"w":21.71,"t":24.4},"q4":{"w":12.39,"t":14.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":57.7,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"Qwen/Qwen-Image-Edit-2511","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen-Image-Edit-2511","u":"https://huggingface.co/Qwen/Qwen-Image-Edit-2511"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen-image-edit-2511"},{"id":"qwen-image-edit","name":"Qwen-Image-Edit","hf":"Qwen/Qwen-Image-Edit","org":"Qwen","family":"qwen","series":"Qwen-Image-Edit","task":"image","pipeline":"image-to-image","tags":[],"released":"2025-08-17","updated":"2025-08-25","gated":false,"params":{"total":20.43,"active":null,"src":"safetensors","q":null,"stTotal":20.43},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":40.86,"t":45.4},"fp8":{"w":21.71,"t":24.4},"q4":{"w":12.39,"t":14.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":57.7,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"Qwen/Qwen-Image-Edit","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen-Image-Edit","u":"https://huggingface.co/Qwen/Qwen-Image-Edit"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen-image-edit"},{"id":"qwen-image-edit-2509","name":"Qwen-Image-Edit-2509","hf":"Qwen/Qwen-Image-Edit-2509","org":"Qwen","family":"qwen","series":"Qwen-Image-Edit","task":"image","pipeline":"image-to-image","tags":[],"released":"2025-09-22","updated":"2025-09-22","gated":false,"params":{"total":20.43,"active":null,"src":"safetensors","q":null,"stTotal":20.43},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":40.86,"t":45.4},"fp8":{"w":21.71,"t":24.4},"q4":{"w":12.39,"t":14.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":57.7,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"Qwen/Qwen-Image-Edit-2509","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen-Image-Edit-2509","u":"https://huggingface.co/Qwen/Qwen-Image-Edit-2509"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen-image-edit-2509"},{"id":"qwen-image-layered","name":"Qwen-Image-Layered","hf":"Qwen/Qwen-Image-Layered","org":"Qwen","family":"qwen","series":"Qwen-Image-Layered","task":"image","pipeline":"image-text-to-image","tags":[],"released":"2025-12-17","updated":"2025-12-19","gated":false,"params":{"total":20.43,"active":null,"src":"safetensors","q":null,"stTotal":20.43},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":40.86,"t":45.4},"fp8":{"w":21.71,"t":24.4},"q4":{"w":12.39,"t":14.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac128"},"fp8":{"gpu":"rtx5090","mac":"mac64"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":57.7,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"Qwen/Qwen-Image-Layered","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen-Image-Layered","u":"https://huggingface.co/Qwen/Qwen-Image-Layered"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen-image-layered"},{"id":"qwen2-0-5b-instruct","name":"Qwen2-0.5B-Instruct","hf":"Qwen/Qwen2-0.5B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-06-03","updated":"2024-08-21","gated":false,"params":{"total":0.494,"active":null,"src":"safetensors","q":null,"stTotal":0.494},"moe":false,"ctx":32768,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":256,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":0.99,"t":1.7},"fp8":{"w":0.52,"t":1.2},"q4":{"w":0.3,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.99,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2-0.5B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"},{"id":"ollama","via":"ollama-library","tag":"qwen2:0.5b","url":"https://ollama.com/library/qwen2"}],"variants":[{"id":"Qwen/Qwen2-0.5B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2-0.5B","kind":"main"},{"id":"Qwen/Qwen2-0.5B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2-0.5B-Instruct-MLX","kind":"Instruct/MLX"},{"id":"Qwen/Qwen2-0.5B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2-0.5B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2-0.5B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2-0.5B-Instruct","u":"https://huggingface.co/Qwen/Qwen2-0.5B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2-0.5B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2-0.5B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2","u":"https://ollama.com/library/qwen2"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-0-5b-instruct"},{"id":"qwen2-1-5b-instruct","name":"Qwen2-1.5B-Instruct","hf":"Qwen/Qwen2-1.5B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-06-03","updated":"2024-06-06","gated":false,"params":{"total":1.544,"active":null,"src":"safetensors","q":null,"stTotal":1.544},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.23,"32768":0.94},"mem":{"bf16":{"w":3.09,"t":4.1},"fp8":{"w":1.64,"t":2.5},"q4":{"w":0.94,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.09,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2-1.5B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"},{"id":"ollama","via":"ollama-library","tag":"qwen2:1.5b","url":"https://ollama.com/library/qwen2"}],"variants":[{"id":"Qwen/Qwen2-1.5B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2-1.5B","kind":"main"},{"id":"Qwen/Qwen2-1.5B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2-1.5B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2-1.5B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2-1.5B-Instruct-MLX","kind":"Instruct/MLX"},{"id":"Qwen/Qwen2-1.5B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2-1.5B-Instruct","u":"https://huggingface.co/Qwen/Qwen2-1.5B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2-1.5B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2-1.5B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2","u":"https://ollama.com/library/qwen2"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-1-5b-instruct"},{"id":"qwen2-7b","name":"Qwen2-7B","hf":"Qwen/Qwen2-7B","org":"Qwen","family":"qwen","series":"Qwen2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-06-04","updated":"2024-06-06","gated":false,"params":{"total":7.616,"active":null,"src":"safetensors","q":null,"stTotal":7.616},"moe":false,"ctx":131072,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88,"131072":7.52},"mem":{"bf16":{"w":15.23,"t":17.7},"fp8":{"w":8.09,"t":9.9},"q4":{"w":4.62,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.23,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2-7B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"},{"id":"ollama","via":"ollama-library","tag":"qwen2:7b","url":"https://ollama.com/library/qwen2"}],"variants":[{"id":"Qwen/Qwen2-7B","kind":"main"},{"id":"Qwen/Qwen2-7B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2-7B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2-7B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2-7B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2-7B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"},{"id":"Qwen/Qwen2-7B-Instruct-MLX","kind":"Instruct/MLX"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2-7B","u":"https://huggingface.co/Qwen/Qwen2-7B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2-7B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2-7B/blob/main/LICENSE"},{"t":"Ollama library · qwen2","u":"https://ollama.com/library/qwen2"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-7b"},{"id":"qwen2-57b-a14b-instruct","name":"Qwen2-57B-A14B-Instruct","hf":"Qwen/Qwen2-57B-A14B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-06-04","updated":"2024-08-21","gated":false,"params":{"total":57.409,"active":14,"src":"safetensors","q":null,"stTotal":57.409},"moe":true,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":114.82,"t":127.3},"fp8":{"w":61,"t":68.1},"q4":{"w":34.8,"t":39.3}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"h100","mac":"mac128"},"q4":{"gpu":"2x5090","mac":"mac64"}},"disk":114.82,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"Qwen/Qwen2-57B-A14B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2-57B-A14B","kind":"main"},{"id":"Qwen/Qwen2-57B-A14B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2-57B-A14B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2-57B-A14B-Instruct","u":"https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-57b-a14b-instruct"},{"id":"qwen2-72b","name":"Qwen2-72B","hf":"Qwen/Qwen2-72B","org":"Qwen","family":"qwen","series":"Qwen2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-22","updated":"2024-10-09","gated":false,"params":{"total":72.706,"active":null,"src":"safetensors","q":null,"stTotal":72.706},"moe":false,"ctx":131072,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74,"131072":42.95},"mem":{"bf16":{"w":145.41,"t":163.1},"fp8":{"w":77.25,"t":88.2},"q4":{"w":44.08,"t":51.7}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":145.41,"native":"BF16","license":{"id":"tongyi-qianwen","name":"tongyi-qianwen","link":"https://huggingface.co/Qwen/Qwen2-72B/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2:72b","url":"https://ollama.com/library/qwen2"}],"variants":[{"id":"Qwen/Qwen2-72B","kind":"main"},{"id":"Qwen/Qwen2-72B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2-72B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2-72B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2-72B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"},{"id":"Qwen/Qwen2-72B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2-72B","u":"https://huggingface.co/Qwen/Qwen2-72B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2-72B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2-72B/blob/main/LICENSE"},{"t":"Ollama library · qwen2","u":"https://ollama.com/library/qwen2"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-72b"},{"id":"qwen2-audio-7b-instruct","name":"Qwen2-Audio-7B-Instruct","hf":"Qwen/Qwen2-Audio-7B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2-Audio","task":"omni","pipeline":"audio-text-to-text","tags":[],"released":"2024-07-31","updated":"2025-01-12","gated":false,"params":{"total":8.397,"active":null,"src":"safetensors","q":null,"stTotal":8.397},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":16.79,"t":19},"fp8":{"w":8.92,"t":10.3},"q4":{"w":5.09,"t":6.1}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.79,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen2-Audio-7B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2-Audio-7B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2-Audio-7B-Instruct","u":"https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-audio-7b-instruct"},{"id":"qwen2-math-1-5b","name":"Qwen2-Math-1.5B","hf":"Qwen/Qwen2-Math-1.5B","org":"Qwen","family":"qwen","series":"Qwen2-Math","task":"llm","pipeline":"text-generation","tags":["math"],"released":"2024-08-08","updated":"2024-08-08","gated":false,"params":{"total":1.544,"active":null,"src":"safetensors","q":null,"stTotal":1.544},"moe":false,"ctx":4096,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.23},"mem":{"bf16":{"w":3.09,"t":4.1},"fp8":{"w":1.64,"t":2.5},"q4":{"w":0.94,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.09,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen2-math:1.5b","url":"https://ollama.com/library/qwen2-math"}],"variants":[{"id":"Qwen/Qwen2-Math-1.5B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2-Math-1.5B","u":"https://huggingface.co/Qwen/Qwen2-Math-1.5B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2-Math-1.5B/blob/main/config.json"},{"t":"Ollama library · qwen2-math","u":"https://ollama.com/library/qwen2-math"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-math-1-5b"},{"id":"qwen2-vl-2b-instruct","name":"Qwen2-VL-2B-Instruct","hf":"Qwen/Qwen2-VL-2B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-08-28","updated":"2025-01-12","gated":false,"params":{"total":2.209,"active":null,"src":"safetensors","q":null,"stTotal":2.209},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.23,"32768":0.94},"mem":{"bf16":{"w":4.42,"t":5.6},"fp8":{"w":2.35,"t":3.3},"q4":{"w":1.34,"t":2.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.42,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen2-VL-2B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2-VL-2B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2-VL-2B","kind":"main"},{"id":"Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2-VL-2B-Instruct","u":"https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-vl-2b-instruct"},{"id":"qwen2-vl-7b-instruct","name":"Qwen2-VL-7B-Instruct","hf":"Qwen/Qwen2-VL-7B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-08-28","updated":"2025-02-06","gated":false,"params":{"total":8.291,"active":null,"src":"safetensors","q":null,"stTotal":8.291},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":16.58,"t":19.2},"fp8":{"w":8.81,"t":10.7},"q4":{"w":5.03,"t":6.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.58,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen2-VL-7B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2-VL-7B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2-VL-7B","kind":"main"},{"id":"Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2-VL-7B-Instruct","u":"https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-vl-7b-instruct"},{"id":"qwen2-vl-72b-instruct","name":"Qwen2-VL-72B-Instruct","hf":"Qwen/Qwen2-VL-72B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2024-09-17","updated":"2025-02-06","gated":false,"params":{"total":73.406,"active":null,"src":"safetensors","q":null,"stTotal":73.406},"moe":false,"ctx":32768,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74},"mem":{"bf16":{"w":146.81,"t":164.7},"fp8":{"w":77.99,"t":89},"q4":{"w":44.5,"t":52.1}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":146.81,"native":"BF16","license":{"id":"tongyi-qianwen","name":"tongyi-qianwen","link":"https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen2-VL-72B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2-VL-72B","kind":"main"},{"id":"Qwen/Qwen2-VL-72B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"},{"id":"Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2-VL-72B-Instruct","u":"https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-vl-72b-instruct"},{"id":"qwen2-5-0-5b-instruct","name":"Qwen2.5-0.5B-Instruct","hf":"Qwen/Qwen2.5-0.5B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-16","updated":"2024-09-25","gated":false,"params":{"total":0.494,"active":null,"src":"safetensors","q":null,"stTotal":0.494},"moe":false,"ctx":32768,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":256,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":0.99,"t":1.7},"fp8":{"w":0.52,"t":1.2},"q4":{"w":0.3,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.99,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5:0.5b","url":"https://ollama.com/library/qwen2.5"}],"variants":[{"id":"Qwen/Qwen2.5-0.5B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-0.5B","kind":"main"},{"id":"Qwen/Qwen2.5-0.5B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-0.5B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-0.5B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5","u":"https://ollama.com/library/qwen2.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-0-5b-instruct"},{"id":"qwen2-5-1-5b-instruct","name":"Qwen2.5-1.5B-Instruct","hf":"Qwen/Qwen2.5-1.5B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-17","updated":"2024-09-25","gated":false,"params":{"total":1.544,"active":null,"src":"safetensors","q":null,"stTotal":1.544},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.23,"32768":0.94},"mem":{"bf16":{"w":3.09,"t":4.1},"fp8":{"w":1.64,"t":2.5},"q4":{"w":0.94,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.09,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5:1.5b","url":"https://ollama.com/library/qwen2.5"}],"variants":[{"id":"Qwen/Qwen2.5-1.5B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-1.5B","kind":"main"},{"id":"Qwen/Qwen2.5-1.5B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-1.5B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-1.5B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5","u":"https://ollama.com/library/qwen2.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-1-5b-instruct"},{"id":"qwen2-5-3b-instruct","name":"Qwen2.5-3B-Instruct","hf":"Qwen/Qwen2.5-3B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-17","updated":"2024-09-25","gated":false,"params":{"total":3.086,"active":null,"src":"safetensors","q":null,"stTotal":3.086},"moe":false,"ctx":32768,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.3,"32768":1.21},"mem":{"bf16":{"w":6.17,"t":7.6},"fp8":{"w":3.28,"t":4.4},"q4":{"w":1.87,"t":2.9}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.17,"native":"BF16","license":{"id":"qwen-research","name":"qwen-research","link":"https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5:3b","url":"https://ollama.com/library/qwen2.5"}],"variants":[{"id":"Qwen/Qwen2.5-3B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-3B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-3B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-3B","kind":"main"},{"id":"Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-3B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-3B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5","u":"https://ollama.com/library/qwen2.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-3b-instruct"},{"id":"qwen2-5-7b-instruct","name":"Qwen2.5-7B-Instruct","hf":"Qwen/Qwen2.5-7B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-16","updated":"2025-01-12","gated":false,"params":{"total":7.616,"active":null,"src":"safetensors","q":null,"stTotal":7.616},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":15.23,"t":17.7},"fp8":{"w":8.09,"t":9.9},"q4":{"w":4.62,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.23,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5:7b","url":"https://ollama.com/library/qwen2.5"}],"variants":[{"id":"Qwen/Qwen2.5-7B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-7B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-7B","kind":"main"},{"id":"Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-7B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-7B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5","u":"https://ollama.com/library/qwen2.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-7b-instruct"},{"id":"qwen2-5-7b-instruct-1m","name":"Qwen2.5-7B-Instruct-1M","hf":"Qwen/Qwen2.5-7B-Instruct-1M","org":"Qwen","family":"qwen","series":"Qwen2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-01-23","updated":"2025-01-29","gated":false,"params":{"total":7.616,"active":null,"src":"safetensors","q":null,"stTotal":7.616},"moe":false,"ctx":1010000,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88,"131072":7.52},"mem":{"bf16":{"w":15.23,"t":17.7},"fp8":{"w":8.09,"t":9.9},"q4":{"w":4.62,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.23,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen2.5-7B-Instruct-1M","kind":"Instruct"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-7B-Instruct-1M","u":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-7b-instruct-1m"},{"id":"qwen2-5-14b-instruct","name":"Qwen2.5-14B-Instruct","hf":"Qwen/Qwen2.5-14B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-16","updated":"2024-09-25","gated":false,"params":{"total":14.77,"active":null,"src":"safetensors","q":null,"stTotal":14.77},"moe":false,"ctx":32768,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.61,"32768":6.44},"mem":{"bf16":{"w":29.54,"t":34.6},"fp8":{"w":15.69,"t":19.4},"q4":{"w":8.95,"t":12}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":29.54,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5:14b","url":"https://ollama.com/library/qwen2.5"}],"variants":[{"id":"Qwen/Qwen2.5-14B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-14B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-14B","kind":"main"},{"id":"Qwen/Qwen2.5-14B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-14B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-14B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5","u":"https://ollama.com/library/qwen2.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-14b-instruct"},{"id":"qwen2-5-14b-instruct-1m","name":"Qwen2.5-14B-Instruct-1M","hf":"Qwen/Qwen2.5-14B-Instruct-1M","org":"Qwen","family":"qwen","series":"Qwen2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-01-23","updated":"2025-01-29","gated":false,"params":{"total":14.77,"active":null,"src":"safetensors","q":null,"stTotal":14.77},"moe":false,"ctx":1010000,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.61,"32768":6.44,"131072":25.77},"mem":{"bf16":{"w":29.54,"t":34.6},"fp8":{"w":15.69,"t":19.4},"q4":{"w":8.95,"t":12}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":29.54,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-1M/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen2.5-14B-Instruct-1M","kind":"Instruct"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-14B-Instruct-1M","u":"https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-1M"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-1M/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-1M/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-14b-instruct-1m"},{"id":"qwen2-5-32b-instruct","name":"Qwen2.5-32B-Instruct","hf":"Qwen/Qwen2.5-32B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-17","updated":"2024-09-25","gated":false,"params":{"total":32.764,"active":null,"src":"safetensors","q":null,"stTotal":32.764},"moe":false,"ctx":32768,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59},"mem":{"bf16":{"w":65.53,"t":74.7},"fp8":{"w":34.81,"t":40.9},"q4":{"w":19.86,"t":24.5}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":65.53,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5:32b","url":"https://ollama.com/library/qwen2.5"}],"variants":[{"id":"Qwen/Qwen2.5-32B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-32B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-32B","kind":"main"},{"id":"Qwen/Qwen2.5-32B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-32B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-32B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5","u":"https://ollama.com/library/qwen2.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-32b-instruct"},{"id":"qwen2-5-72b-instruct","name":"Qwen2.5-72B-Instruct","hf":"Qwen/Qwen2.5-72B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-09-16","updated":"2025-01-12","gated":false,"params":{"total":72.706,"active":null,"src":"safetensors","q":null,"stTotal":72.706},"moe":false,"ctx":32768,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74},"mem":{"bf16":{"w":145.41,"t":163.1},"fp8":{"w":77.25,"t":88.2},"q4":{"w":44.08,"t":51.7}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":145.41,"native":"BF16","license":{"id":"qwen","name":"qwen","link":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5:72b","url":"https://ollama.com/library/qwen2.5"}],"variants":[{"id":"Qwen/Qwen2.5-72B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-72B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-72B","kind":"main"},{"id":"Qwen/Qwen2.5-72B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-72B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5","u":"https://ollama.com/library/qwen2.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-72b-instruct"},{"id":"qwen2-5-coder-0-5b-instruct","name":"Qwen2.5-Coder-0.5B-Instruct","hf":"Qwen/Qwen2.5-Coder-0.5B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-11-06","updated":"2024-11-18","gated":false,"params":{"total":0.494,"active":null,"src":"safetensors","q":null,"stTotal":0.494},"moe":false,"ctx":32768,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":256,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.1,"32768":0.4},"mem":{"bf16":{"w":0.99,"t":1.7},"fp8":{"w":0.52,"t":1.2},"q4":{"w":0.3,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.99,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5-coder:0.5b","url":"https://ollama.com/library/qwen2.5-coder"}],"variants":[{"id":"Qwen/Qwen2.5-Coder-0.5B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-Coder-0.5B","kind":"main"},{"id":"Qwen/Qwen2.5-Coder-0.5B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-Coder-0.5B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5-coder","u":"https://ollama.com/library/qwen2.5-coder"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-coder-0-5b-instruct"},{"id":"qwen2-5-coder-1-5b-instruct","name":"Qwen2.5-Coder-1.5B-Instruct","hf":"Qwen/Qwen2.5-Coder-1.5B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-09-18","updated":"2025-01-12","gated":false,"params":{"total":1.544,"active":null,"src":"safetensors","q":null,"stTotal":1.544},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.23,"32768":0.94},"mem":{"bf16":{"w":3.09,"t":4.1},"fp8":{"w":1.64,"t":2.5},"q4":{"w":0.94,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.09,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5-coder:1.5b","url":"https://ollama.com/library/qwen2.5-coder"}],"variants":[{"id":"Qwen/Qwen2.5-Coder-1.5B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-Coder-1.5B","kind":"main"},{"id":"Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-Coder-1.5B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5-coder","u":"https://ollama.com/library/qwen2.5-coder"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-coder-1-5b-instruct"},{"id":"qwen2-5-coder-3b-instruct","name":"Qwen2.5-Coder-3B-Instruct","hf":"Qwen/Qwen2.5-Coder-3B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-11-06","updated":"2025-01-12","gated":false,"params":{"total":3.086,"active":null,"src":"safetensors","q":null,"stTotal":3.086},"moe":false,"ctx":32768,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.3,"32768":1.21},"mem":{"bf16":{"w":6.17,"t":7.6},"fp8":{"w":3.28,"t":4.4},"q4":{"w":1.87,"t":2.9}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.17,"native":"BF16","license":{"id":"qwen-research","name":"qwen-research","link":"https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5-coder:3b","url":"https://ollama.com/library/qwen2.5-coder"}],"variants":[{"id":"Qwen/Qwen2.5-Coder-3B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-Coder-3B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-Coder-3B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-Coder-3B","kind":"main"},{"id":"Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-Coder-3B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5-coder","u":"https://ollama.com/library/qwen2.5-coder"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-coder-3b-instruct"},{"id":"qwen2-5-coder-7b-instruct","name":"Qwen2.5-Coder-7B-Instruct","hf":"Qwen/Qwen2.5-Coder-7B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-09-17","updated":"2025-01-12","gated":false,"params":{"total":7.616,"active":null,"src":"safetensors","q":null,"stTotal":7.616},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":15.23,"t":17.7},"fp8":{"w":8.09,"t":9.9},"q4":{"w":4.62,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.23,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5-coder:7b","url":"https://ollama.com/library/qwen2.5-coder"}],"variants":[{"id":"Qwen/Qwen2.5-Coder-7B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-Coder-7B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-Coder-7B","kind":"main"},{"id":"Qwen/Qwen2.5-Coder-7B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-Coder-7B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5-coder","u":"https://ollama.com/library/qwen2.5-coder"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-coder-7b-instruct"},{"id":"qwen2-5-coder-14b-instruct","name":"Qwen2.5-Coder-14B-Instruct","hf":"Qwen/Qwen2.5-Coder-14B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-11-06","updated":"2025-01-12","gated":false,"params":{"total":14.77,"active":null,"src":"safetensors","q":null,"stTotal":14.77},"moe":false,"ctx":32768,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.61,"32768":6.44},"mem":{"bf16":{"w":29.54,"t":34.6},"fp8":{"w":15.69,"t":19.4},"q4":{"w":8.95,"t":12}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":29.54,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5-coder:14b","url":"https://ollama.com/library/qwen2.5-coder"}],"variants":[{"id":"Qwen/Qwen2.5-Coder-14B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-Coder-14B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-Coder-14B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-Coder-14B","kind":"main"},{"id":"Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-Coder-14B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5-coder","u":"https://ollama.com/library/qwen2.5-coder"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-coder-14b-instruct"},{"id":"qwen2-5-coder-32b-instruct","name":"Qwen2.5-Coder-32B-Instruct","hf":"Qwen/Qwen2.5-Coder-32B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-11-06","updated":"2025-01-12","gated":false,"params":{"total":32.764,"active":null,"src":"safetensors","q":null,"stTotal":32.764},"moe":false,"ctx":32768,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59},"mem":{"bf16":{"w":65.53,"t":74.7},"fp8":{"w":34.81,"t":40.9},"q4":{"w":19.86,"t":24.5}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":65.53,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5-coder:32b","url":"https://ollama.com/library/qwen2.5-coder"}],"variants":[{"id":"Qwen/Qwen2.5-Coder-32B-Instruct-AWQ","kind":"Instruct/AWQ"},{"id":"Qwen/Qwen2.5-Coder-32B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-Coder-32B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen2.5-Coder-32B","kind":"main"},{"id":"Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4","kind":"Instruct/GPTQ/INT4"},{"id":"Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8","kind":"Instruct/GPTQ/INT8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-Coder-32B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5-coder","u":"https://ollama.com/library/qwen2.5-coder"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-coder-32b-instruct"},{"id":"qwen2-5-math-1-5b","name":"Qwen2.5-Math-1.5B","hf":"Qwen/Qwen2.5-Math-1.5B","org":"Qwen","family":"qwen","series":"Qwen2.5-Math","task":"llm","pipeline":"text-generation","tags":["math"],"released":"2024-09-16","updated":"2024-09-23","gated":false,"params":{"total":1.544,"active":null,"src":"safetensors","q":null,"stTotal":1.544},"moe":false,"ctx":4096,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.23},"mem":{"bf16":{"w":3.09,"t":4.1},"fp8":{"w":1.64,"t":2.5},"q4":{"w":0.94,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.09,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-Math-1.5B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen2.5-Math-1.5B","kind":"main"},{"id":"Qwen/Qwen2.5-Math-1.5B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-Math-1.5B","u":"https://huggingface.co/Qwen/Qwen2.5-Math-1.5B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-Math-1.5B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-Math-1.5B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-math-1-5b"},{"id":"qwen2-5-math-7b-instruct","name":"Qwen2.5-Math-7B-Instruct","hf":"Qwen/Qwen2.5-Math-7B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-Math","task":"llm","pipeline":"text-generation","tags":["math"],"released":"2024-09-19","updated":"2024-09-23","gated":false,"params":{"total":7.616,"active":null,"src":"safetensors","q":null,"stTotal":7.616},"moe":false,"ctx":4096,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47},"mem":{"bf16":{"w":15.23,"t":17.7},"fp8":{"w":8.09,"t":9.9},"q4":{"w":4.62,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.23,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen2.5-Math-7B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-Math-7B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-Math-7B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-math-7b-instruct"},{"id":"qwen2-5-math-72b-instruct","name":"Qwen2.5-Math-72B-Instruct","hf":"Qwen/Qwen2.5-Math-72B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-Math","task":"llm","pipeline":"text-generation","tags":["math"],"released":"2024-09-16","updated":"2024-09-23","gated":false,"params":{"total":72.706,"active":null,"src":"safetensors","q":null,"stTotal":72.706},"moe":false,"ctx":4096,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68},"mem":{"bf16":{"w":145.41,"t":163.1},"fp8":{"w":77.25,"t":88.2},"q4":{"w":44.08,"t":51.7}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":145.41,"native":"BF16","license":{"id":"qwen","name":"qwen","link":"https://huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen2.5-Math-72B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-Math-72B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-math-72b-instruct"},{"id":"qwen2-5-omni-3b","name":"Qwen2.5-Omni-3B","hf":"Qwen/Qwen2.5-Omni-3B","org":"Qwen","family":"qwen","series":"Qwen2.5-Omni","task":"omni","pipeline":"any-to-any","tags":[],"released":"2025-04-30","updated":"2025-04-30","gated":false,"params":{"total":5.537,"active":null,"src":"safetensors","q":null,"stTotal":5.537},"moe":false,"ctx":32768,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.3,"32768":1.21},"mem":{"bf16":{"w":11.07,"t":13},"fp8":{"w":5.88,"t":7.3},"q4":{"w":3.36,"t":4.5}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":11.97,"native":"BF16","license":{"id":"qwen-research","name":"qwen-research","link":"https://huggingface.co/Qwen/Qwen2.5-Omni-3B/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen2.5-Omni-3B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-Omni-3B","u":"https://huggingface.co/Qwen/Qwen2.5-Omni-3B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-Omni-3B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-Omni-3B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-omni-3b"},{"id":"qwen2-5-omni-7b","name":"Qwen2.5-Omni-7B","hf":"Qwen/Qwen2.5-Omni-7B","org":"Qwen","family":"qwen","series":"Qwen2.5-Omni","task":"omni","pipeline":"any-to-any","tags":[],"released":"2025-03-22","updated":"2025-04-30","gated":false,"params":{"total":10.732,"active":null,"src":"safetensors","q":null,"stTotal":10.732},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":21.46,"t":24.6},"fp8":{"w":11.4,"t":13.5},"q4":{"w":6.51,"t":8.1}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":22.36,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen2.5-Omni-7B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen2.5-Omni-7B","kind":"main"},{"id":"Qwen/Qwen2.5-Omni-7B-AWQ","kind":"AWQ"},{"id":"Qwen/Qwen2.5-Omni-7B-GPTQ-Int4","kind":"GPTQ/INT4"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-Omni-7B","u":"https://huggingface.co/Qwen/Qwen2.5-Omni-7B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-Omni-7B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-Omni-7B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-omni-7b"},{"id":"qwen2-5-vl-3b-instruct","name":"Qwen2.5-VL-3B-Instruct","hf":"Qwen/Qwen2.5-VL-3B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-01-26","updated":"2025-04-06","gated":false,"params":{"total":3.755,"active":null,"src":"safetensors","q":null,"stTotal":3.755},"moe":false,"ctx":128000,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":512,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.3,"32768":1.21},"mem":{"bf16":{"w":7.51,"t":9.1},"fp8":{"w":3.99,"t":5.2},"q4":{"w":2.28,"t":3.3}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.51,"native":"BF16","license":{"id":"qwen-research","name":"qwen-research","link":"https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5vl:3b","url":"https://ollama.com/library/qwen2.5vl"}],"variants":[{"id":"Qwen/Qwen2.5-VL-3B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-VL-3B-Instruct-AWQ","kind":"Instruct/AWQ"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-VL-3B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5vl","u":"https://ollama.com/library/qwen2.5vl"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-vl-3b-instruct"},{"id":"qwen2-5-vl-7b-instruct","name":"Qwen2.5-VL-7B-Instruct","hf":"Qwen/Qwen2.5-VL-7B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-01-26","updated":"2025-04-06","gated":false,"params":{"total":8.292,"active":null,"src":"safetensors","q":null,"stTotal":8.292},"moe":false,"ctx":128000,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":16.58,"t":19.2},"fp8":{"w":8.81,"t":10.7},"q4":{"w":5.03,"t":6.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.58,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5vl:7b","url":"https://ollama.com/library/qwen2.5vl"}],"variants":[{"id":"Qwen/Qwen2.5-VL-7B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-VL-7B-Instruct-AWQ","kind":"Instruct/AWQ"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-VL-7B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct/blob/main/config.json"},{"t":"Ollama library · qwen2.5vl","u":"https://ollama.com/library/qwen2.5vl"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-vl-7b-instruct"},{"id":"qwen2-5-vl-32b-instruct","name":"Qwen2.5-VL-32B-Instruct","hf":"Qwen/Qwen2.5-VL-32B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-03-21","updated":"2025-04-14","gated":false,"params":{"total":33.453,"active":null,"src":"safetensors","q":null,"stTotal":33.453},"moe":false,"ctx":128000,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59},"mem":{"bf16":{"w":66.91,"t":76.2},"fp8":{"w":35.54,"t":41.7},"q4":{"w":20.28,"t":25}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":68.28,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5vl:32b","url":"https://ollama.com/library/qwen2.5vl"}],"variants":[{"id":"Qwen/Qwen2.5-VL-32B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-VL-32B-Instruct-AWQ","kind":"Instruct/AWQ"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-VL-32B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct/blob/main/config.json"},{"t":"Ollama library · qwen2.5vl","u":"https://ollama.com/library/qwen2.5vl"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-vl-32b-instruct"},{"id":"qwen2-5-vl-72b-instruct","name":"Qwen2.5-VL-72B-Instruct","hf":"Qwen/Qwen2.5-VL-72B-Instruct","org":"Qwen","family":"qwen","series":"Qwen2.5-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-01-27","updated":"2025-06-06","gated":false,"params":{"total":73.411,"active":null,"src":"safetensors","q":null,"stTotal":73.411},"moe":false,"ctx":128000,"arch":{"L":80,"attn":80,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.68,"32768":10.74},"mem":{"bf16":{"w":146.82,"t":164.7},"fp8":{"w":78,"t":89},"q4":{"w":44.51,"t":52.1}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac256"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":146.82,"native":"BF16","license":{"id":"qwen","name":"qwen","link":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen2.5vl:72b","url":"https://ollama.com/library/qwen2.5vl"}],"variants":[{"id":"Qwen/Qwen2.5-VL-72B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen2.5-VL-72B-Instruct-AWQ","kind":"Instruct/AWQ"}],"sources":[{"t":"Hugging Face · Qwen/Qwen2.5-VL-72B-Instruct","u":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct/blob/main/LICENSE"},{"t":"Ollama library · qwen2.5vl","u":"https://ollama.com/library/qwen2.5vl"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen2-5-vl-72b-instruct"},{"id":"qwen3-0-6b","name":"Qwen3-0.6B","hf":"Qwen/Qwen3-0.6B","org":"Qwen","family":"qwen","series":"Qwen3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-27","updated":"2025-07-26","gated":false,"params":{"total":0.752,"active":null,"src":"safetensors","q":null,"stTotal":0.752},"moe":false,"ctx":40960,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.94,"32768":3.76},"mem":{"bf16":{"w":1.5,"t":3.1},"fp8":{"w":0.8,"t":2.3},"q4":{"w":0.46,"t":1.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.5,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3:0.6b","url":"https://ollama.com/library/qwen3"}],"variants":[{"id":"Qwen/Qwen3-0.6B","kind":"main"},{"id":"Qwen/Qwen3-0.6B-Base","kind":"Base"},{"id":"Qwen/Qwen3-0.6B-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-Embedding-0.6B-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-0.6B-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-0.6B-MLX-4bit","kind":"MLX"},{"id":"Qwen/Qwen3-0.6B-GPTQ-Int8","kind":"GPTQ/INT8"},{"id":"Qwen/Qwen3-0.6B-MLX-8bit","kind":"MLX"},{"id":"Qwen/Qwen3-0.6B-MLX-bf16","kind":"MLX/BF16"},{"id":"Qwen/Qwen3-0.6B-MLX-6bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-0.6B","u":"https://huggingface.co/Qwen/Qwen3-0.6B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE"},{"t":"Ollama library · qwen3","u":"https://ollama.com/library/qwen3"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-0-6b"},{"id":"qwen3-1-7b","name":"Qwen3-1.7B","hf":"Qwen/Qwen3-1.7B","org":"Qwen","family":"qwen","series":"Qwen3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-27","updated":"2025-07-26","gated":false,"params":{"total":2.032,"active":null,"src":"safetensors","q":null,"stTotal":2.032},"moe":false,"ctx":40960,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.94,"32768":3.76},"mem":{"bf16":{"w":4.06,"t":5.9},"fp8":{"w":2.16,"t":3.8},"q4":{"w":1.23,"t":2.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.06,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3:1.7b","url":"https://ollama.com/library/qwen3"}],"variants":[{"id":"Qwen/Qwen3-1.7B","kind":"main"},{"id":"Qwen/Qwen3-1.7B-Base","kind":"Base"},{"id":"Qwen/Qwen3-1.7B-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-1.7B-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-1.7B-MLX-4bit","kind":"MLX"},{"id":"Qwen/Qwen3-1.7B-GPTQ-Int8","kind":"GPTQ/INT8"},{"id":"Qwen/Qwen3-1.7B-MLX-8bit","kind":"MLX"},{"id":"Qwen/Qwen3-1.7B-MLX-bf16","kind":"MLX/BF16"},{"id":"Qwen/Qwen3-1.7B-MLX-6bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-1.7B","u":"https://huggingface.co/Qwen/Qwen3-1.7B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE"},{"t":"Ollama library · qwen3","u":"https://ollama.com/library/qwen3"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-1-7b"},{"id":"qwen3-4b","name":"Qwen3-4B","hf":"Qwen/Qwen3-4B","org":"Qwen","family":"qwen","series":"Qwen3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-27","updated":"2025-07-26","gated":false,"params":{"total":4.022,"active":null,"src":"safetensors","q":null,"stTotal":4.022},"moe":false,"ctx":40960,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":8.04,"t":10.6},"fp8":{"w":4.27,"t":6.4},"q4":{"w":2.44,"t":4.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.04,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3:4b","url":"https://ollama.com/library/qwen3"}],"variants":[{"id":"Qwen/Qwen3-4B","kind":"main"},{"id":"Qwen/Qwen3-4B-Base","kind":"Base"},{"id":"Qwen/Qwen3-4B-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-4B-AWQ","kind":"AWQ"},{"id":"Qwen/Qwen3-4B-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-Embedding-4B-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-4B-MLX-4bit","kind":"MLX"},{"id":"Qwen/Qwen3-4B-MLX-8bit","kind":"MLX"},{"id":"Qwen/Qwen3-4B-MLX-bf16","kind":"MLX/BF16"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-4B","u":"https://huggingface.co/Qwen/Qwen3-4B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-4B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE"},{"t":"Ollama library · qwen3","u":"https://ollama.com/library/qwen3"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-4b"},{"id":"qwen3-4b-instruct-2507","name":"Qwen3-4B-Instruct-2507","hf":"Qwen/Qwen3-4B-Instruct-2507","org":"Qwen","family":"qwen","series":"Qwen3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-08-05","updated":"2025-09-17","gated":false,"params":{"total":4.022,"active":null,"src":"safetensors","q":null,"stTotal":4.022},"moe":false,"ctx":262144,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83,"131072":19.33},"mem":{"bf16":{"w":8.04,"t":10.6},"fp8":{"w":4.27,"t":6.4},"q4":{"w":2.44,"t":4.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.04,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-4B-Instruct-2507","kind":"Instruct"},{"id":"Qwen/Qwen3-4B-Instruct-2507-FP8","kind":"Instruct/FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-4B-Instruct-2507","u":"https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-4b-instruct-2507"},{"id":"qwen3-8b","name":"Qwen3-8B","hf":"Qwen/Qwen3-8B","org":"Qwen","family":"qwen","series":"Qwen3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-27","updated":"2025-07-26","gated":false,"params":{"total":8.191,"active":null,"src":"safetensors","q":null,"stTotal":8.191},"moe":false,"ctx":40960,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":16.38,"t":19.7},"fp8":{"w":8.7,"t":11.3},"q4":{"w":4.97,"t":7.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.38,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3:8b","url":"https://ollama.com/library/qwen3"}],"variants":[{"id":"Qwen/Qwen3-8B","kind":"main"},{"id":"Qwen/Qwen3-8B-AWQ","kind":"AWQ"},{"id":"Qwen/Qwen3-8B-Base","kind":"Base"},{"id":"Qwen/Qwen3-8B-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-8B-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-Embedding-8B-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-8B-MLX-4bit","kind":"MLX"},{"id":"Qwen/Qwen3-8B-MLX-8bit","kind":"MLX"},{"id":"Qwen/Qwen3-8B-MLX-bf16","kind":"MLX/BF16"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-8B","u":"https://huggingface.co/Qwen/Qwen3-8B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-8B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE"},{"t":"Ollama library · qwen3","u":"https://ollama.com/library/qwen3"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-8b"},{"id":"qwen3-14b","name":"Qwen3-14B","hf":"Qwen/Qwen3-14B","org":"Qwen","family":"qwen","series":"Qwen3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-27","updated":"2025-07-26","gated":false,"params":{"total":14.768,"active":null,"src":"safetensors","q":null,"stTotal":14.768},"moe":false,"ctx":40960,"arch":{"L":40,"attn":40,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.34,"32768":5.37},"mem":{"bf16":{"w":29.54,"t":34.3},"fp8":{"w":15.69,"t":19.1},"q4":{"w":8.95,"t":11.7}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":29.54,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-14B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3:14b","url":"https://ollama.com/library/qwen3"}],"variants":[{"id":"Qwen/Qwen3-14B","kind":"main"},{"id":"Qwen/Qwen3-14B-AWQ","kind":"AWQ"},{"id":"Qwen/Qwen3-14B-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-14B-Base","kind":"Base"},{"id":"Qwen/Qwen3-14B-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-14B-MLX-4bit","kind":"MLX"},{"id":"Qwen/Qwen3-14B-MLX-8bit","kind":"MLX"},{"id":"Qwen/Qwen3-14B-MLX-6bit","kind":"MLX"},{"id":"Qwen/Qwen3-14B-MLX-bf16","kind":"MLX/BF16"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-14B","u":"https://huggingface.co/Qwen/Qwen3-14B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-14B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-14B/blob/main/LICENSE"},{"t":"Ollama library · qwen3","u":"https://ollama.com/library/qwen3"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-14b"},{"id":"qwen3-30b-a3b-instruct-2507","name":"Qwen3-30B-A3B-Instruct-2507","hf":"Qwen/Qwen3-30B-A3B-Instruct-2507","org":"Qwen","family":"qwen","series":"Qwen3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-28","updated":"2025-09-17","gated":false,"params":{"total":30.532,"active":3,"src":"safetensors","q":null,"stTotal":30.532},"moe":true,"ctx":262144,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22,"131072":12.88},"mem":{"bf16":{"w":61.06,"t":68.5},"fp8":{"w":32.44,"t":37},"q4":{"w":18.51,"t":21.7}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":61.07,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","kind":"Instruct"},{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507-FP8","kind":"Instruct/FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-30B-A3B-Instruct-2507","u":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-30b-a3b-instruct-2507"},{"id":"qwen3-30b-a3b","name":"Qwen3-30B-A3B","hf":"Qwen/Qwen3-30B-A3B","org":"Qwen","family":"qwen","series":"Qwen3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-27","updated":"2025-07-26","gated":false,"params":{"total":30.532,"active":3,"src":"safetensors","q":null,"stTotal":30.532},"moe":true,"ctx":40960,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22},"mem":{"bf16":{"w":61.06,"t":68.5},"fp8":{"w":32.44,"t":37},"q4":{"w":18.51,"t":21.7}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":61.07,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3:30b-a3b","url":"https://ollama.com/library/qwen3"}],"variants":[{"id":"Qwen/Qwen3-30B-A3B","kind":"main"},{"id":"Qwen/Qwen3-30B-A3B-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-30B-A3B-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-30B-A3B-GPTQ-Int4","kind":"GPTQ/INT4"},{"id":"Qwen/Qwen3-30B-A3B-Base","kind":"Base"},{"id":"Qwen/Qwen3-30B-A3B-MLX-4bit","kind":"MLX"},{"id":"Qwen/Qwen3-30B-A3B-MLX-bf16","kind":"MLX/BF16"},{"id":"Qwen/Qwen3-30B-A3B-MLX-8bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-30B-A3B","u":"https://huggingface.co/Qwen/Qwen3-30B-A3B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE"},{"t":"Ollama library · qwen3","u":"https://ollama.com/library/qwen3"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-30b-a3b"},{"id":"qwen3-32b","name":"Qwen3-32B","hf":"Qwen/Qwen3-32B","org":"Qwen","family":"qwen","series":"Qwen3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-27","updated":"2025-07-26","gated":false,"params":{"total":32.762,"active":null,"src":"safetensors","q":null,"stTotal":32.762},"moe":false,"ctx":40960,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59},"mem":{"bf16":{"w":65.52,"t":74.7},"fp8":{"w":34.81,"t":40.9},"q4":{"w":19.86,"t":24.5}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":65.52,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3:32b","url":"https://ollama.com/library/qwen3"}],"variants":[{"id":"Qwen/Qwen3-32B","kind":"main"},{"id":"Qwen/Qwen3-32B-AWQ","kind":"AWQ"},{"id":"Qwen/Qwen3-32B-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-32B-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-32B-MLX-4bit","kind":"MLX"},{"id":"Qwen/Qwen3-32B-MLX-8bit","kind":"MLX"},{"id":"Qwen/Qwen3-32B-MLX-bf16","kind":"MLX/BF16"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-32B","u":"https://huggingface.co/Qwen/Qwen3-32B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-32B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE"},{"t":"Ollama library · qwen3","u":"https://ollama.com/library/qwen3"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-32b"},{"id":"qwen3-235b-a22b","name":"Qwen3-235B-A22B","hf":"Qwen/Qwen3-235B-A22B","org":"Qwen","family":"qwen","series":"Qwen3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-04-27","updated":"2025-07-26","gated":false,"params":{"total":235.094,"active":22,"src":"safetensors","q":null,"stTotal":235.094},"moe":true,"ctx":40960,"arch":{"L":94,"attn":94,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.58,"32768":6.31},"mem":{"bf16":{"w":470.19,"t":519.3},"fp8":{"w":249.79,"t":276.8},"q4":{"w":142.53,"t":158.9}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":470.19,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-235B-A22B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3:235b-a22b","url":"https://ollama.com/library/qwen3"}],"variants":[{"id":"Qwen/Qwen3-235B-A22B","kind":"main"},{"id":"Qwen/Qwen3-235B-A22B-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-235B-A22B-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-235B-A22B-GPTQ-Int4","kind":"GPTQ/INT4"},{"id":"Qwen/Qwen3-235B-A22B-MLX-4bit","kind":"MLX"},{"id":"Qwen/Qwen3-235B-A22B-MLX-bf16","kind":"MLX/BF16"},{"id":"Qwen/Qwen3-235B-A22B-MLX-8bit","kind":"MLX"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-235B-A22B","u":"https://huggingface.co/Qwen/Qwen3-235B-A22B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-235B-A22B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-235B-A22B/blob/main/LICENSE"},{"t":"Ollama library · qwen3","u":"https://ollama.com/library/qwen3"}],"page":"https://aimap.page/en/models/compute/open-models/qwen3-235b-a22b/"},{"id":"qwen3-235b-a22b-instruct-2507","name":"Qwen3-235B-A22B-Instruct-2507","hf":"Qwen/Qwen3-235B-A22B-Instruct-2507","org":"Qwen","family":"qwen","series":"Qwen3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-21","updated":"2025-09-17","gated":false,"params":{"total":235.094,"active":22,"src":"safetensors","q":null,"stTotal":235.094},"moe":true,"ctx":262144,"arch":{"L":94,"attn":94,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.58,"32768":6.31,"131072":25.23},"mem":{"bf16":{"w":470.19,"t":519.3},"fp8":{"w":249.79,"t":276.8},"q4":{"w":142.53,"t":158.9}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":470.19,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507-FP8","kind":"Instruct/FP8"},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","kind":"Instruct"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-235B-A22B-Instruct-2507","u":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/qwen3-235b-a22b-instruct-2507/"},{"id":"qwen3-asr-0-6b","name":"Qwen3-ASR-0.6B","hf":"Qwen/Qwen3-ASR-0.6B","org":"Qwen","family":"qwen","series":"Qwen3-ASR","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-01-28","updated":"2026-01-30","gated":false,"params":{"total":0.938,"active":null,"src":"safetensors","q":null,"stTotal":0.938},"moe":false,"ctx":65536,"arch":null,"kv":null,"mem":{"bf16":{"w":1.88,"t":2.6},"fp8":{"w":1,"t":1.6},"q4":{"w":0.57,"t":1.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.88,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-ASR-0.6B","kind":"main"},{"id":"Qwen/Qwen3-ASR-0.6B-hf","kind":"HF-transformers"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-ASR-0.6B","u":"https://huggingface.co/Qwen/Qwen3-ASR-0.6B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-ASR-0.6B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-asr-0-6b"},{"id":"qwen3-asr-1-7b","name":"Qwen3-ASR-1.7B","hf":"Qwen/Qwen3-ASR-1.7B","org":"Qwen","family":"qwen","series":"Qwen3-ASR","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2026-01-28","updated":"2026-01-30","gated":false,"params":{"total":2.349,"active":null,"src":"safetensors","q":null,"stTotal":2.349},"moe":false,"ctx":65536,"arch":null,"kv":null,"mem":{"bf16":{"w":4.7,"t":5.7},"fp8":{"w":2.5,"t":3.2},"q4":{"w":1.42,"t":2.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.7,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-ASR-1.7B","kind":"main"},{"id":"Qwen/Qwen3-ASR-1.7B-hf","kind":"HF-transformers"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-ASR-1.7B","u":"https://huggingface.co/Qwen/Qwen3-ASR-1.7B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-ASR-1.7B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-asr-1-7b"},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder-30B-A3B-Instruct","hf":"Qwen/Qwen3-Coder-30B-A3B-Instruct","org":"Qwen","family":"qwen","series":"Qwen3-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2025-07-31","updated":"2025-12-03","gated":false,"params":{"total":30.532,"active":3,"src":"safetensors","q":null,"stTotal":30.532},"moe":true,"ctx":262144,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22,"131072":12.88},"mem":{"bf16":{"w":61.06,"t":68.5},"fp8":{"w":32.44,"t":37},"q4":{"w":18.51,"t":21.7}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":61.07,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8","kind":"Instruct/FP8"},{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Coder-30B-A3B-Instruct","u":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-coder-30b-a3b-instruct"},{"id":"qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder-480B-A35B-Instruct","hf":"Qwen/Qwen3-Coder-480B-A35B-Instruct","org":"Qwen","family":"qwen","series":"Qwen3-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2025-07-22","updated":"2025-08-21","gated":false,"params":{"total":480.155,"active":35,"src":"safetensors","q":null,"stTotal":480.155},"moe":true,"ctx":262144,"arch":{"L":62,"attn":62,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.08,"32768":8.32,"131072":33.29},"mem":{"bf16":{"w":960.31,"t":1058.9},"fp8":{"w":510.16,"t":563.8},"q4":{"w":291.09,"t":322.8}},"fits":{"bf16":{"gpu":"8xb200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":960.31,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","kind":"Instruct/FP8"},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Coder-480B-A35B-Instruct","u":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/qwen3-coder-480b-a35b-instruct/"},{"id":"qwen3-coder-next","name":"Qwen3-Coder-Next","hf":"Qwen/Qwen3-Coder-Next","org":"Qwen","family":"qwen","series":"Qwen3-Coder-Next","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2026-01-30","updated":"2026-02-03","gated":false,"params":{"total":80,"active":3,"src":"card","q":"Number of Parameters: 80B in total and 3B activated","stTotal":79.674},"moe":true,"ctx":262144,"arch":{"L":48,"attn":12,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.2,"32768":0.81,"131072":3.22},"mem":{"bf16":{"w":160,"t":176.7},"fp8":{"w":85,"t":94.2},"q4":{"w":48.5,"t":54.1}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":159.36,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3-coder-next","url":"https://ollama.com/library/qwen3-coder-next"}],"variants":[{"id":"Qwen/Qwen3-Coder-Next-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-Coder-Next","kind":"main"},{"id":"Qwen/Qwen3-Coder-Next-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-Coder-Next-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Coder-Next","u":"https://huggingface.co/Qwen/Qwen3-Coder-Next"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/LICENSE"},{"t":"Ollama library · qwen3-coder-next","u":"https://ollama.com/library/qwen3-coder-next"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-coder-next"},{"id":"qwen3-embedding-0-6b","name":"Qwen3-Embedding-0.6B","hf":"Qwen/Qwen3-Embedding-0.6B","org":"Qwen","family":"qwen","series":"Qwen3-Embedding","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2025-06-03","updated":"2026-04-20","gated":false,"params":{"total":0.596,"active":null,"src":"safetensors","q":null,"stTotal":0.596},"moe":false,"ctx":32768,"arch":null,"kv":null,"mem":{"bf16":{"w":1.19,"t":1.8},"fp8":{"w":0.63,"t":1.2},"q4":{"w":0.36,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.19,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3-embedding:0.6b","url":"https://ollama.com/library/qwen3-embedding"}],"variants":[{"id":"Qwen/Qwen3-Embedding-0.6B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Embedding-0.6B","u":"https://huggingface.co/Qwen/Qwen3-Embedding-0.6B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Embedding-0.6B/blob/main/config.json"},{"t":"Ollama library · qwen3-embedding","u":"https://ollama.com/library/qwen3-embedding"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-embedding-0-6b"},{"id":"qwen3-embedding-4b","name":"Qwen3-Embedding-4B","hf":"Qwen/Qwen3-Embedding-4B","org":"Qwen","family":"qwen","series":"Qwen3-Embedding","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2025-06-03","updated":"2025-06-20","gated":false,"params":{"total":4.022,"active":null,"src":"safetensors","q":null,"stTotal":4.022},"moe":false,"ctx":40960,"arch":null,"kv":null,"mem":{"bf16":{"w":8.04,"t":9.3},"fp8":{"w":4.27,"t":5.2},"q4":{"w":2.44,"t":3.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.04,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3-embedding:4b","url":"https://ollama.com/library/qwen3-embedding"}],"variants":[{"id":"Qwen/Qwen3-Embedding-4B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Embedding-4B","u":"https://huggingface.co/Qwen/Qwen3-Embedding-4B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Embedding-4B/blob/main/config.json"},{"t":"Ollama library · qwen3-embedding","u":"https://ollama.com/library/qwen3-embedding"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-embedding-4b"},{"id":"qwen3-embedding-8b","name":"Qwen3-Embedding-8B","hf":"Qwen/Qwen3-Embedding-8B","org":"Qwen","family":"qwen","series":"Qwen3-Embedding","task":"embedding","pipeline":"feature-extraction","tags":[],"released":"2025-06-03","updated":"2025-07-07","gated":false,"params":{"total":7.567,"active":null,"src":"safetensors","q":null,"stTotal":7.567},"moe":false,"ctx":40960,"arch":null,"kv":null,"mem":{"bf16":{"w":15.13,"t":17.1},"fp8":{"w":8.04,"t":9.3},"q4":{"w":4.59,"t":5.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.13,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-Embedding-8B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3-embedding:8b","url":"https://ollama.com/library/qwen3-embedding"}],"variants":[{"id":"Qwen/Qwen3-Embedding-8B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Embedding-8B","u":"https://huggingface.co/Qwen/Qwen3-Embedding-8B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Embedding-8B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-Embedding-8B/blob/main/LICENSE"},{"t":"Ollama library · qwen3-embedding","u":"https://ollama.com/library/qwen3-embedding"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-embedding-8b"},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen3-Next-80B-A3B-Instruct","hf":"Qwen/Qwen3-Next-80B-A3B-Instruct","org":"Qwen","family":"qwen","series":"Qwen3-Next","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-09-09","updated":"2025-09-17","gated":false,"params":{"total":81.325,"active":3,"src":"safetensors","q":null,"stTotal":81.325},"moe":true,"ctx":262144,"arch":{"L":48,"attn":12,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.2,"32768":0.81,"131072":3.22},"mem":{"bf16":{"w":162.65,"t":179.6},"fp8":{"w":86.41,"t":95.7},"q4":{"w":49.3,"t":54.9}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":162.66,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct-FP8","kind":"Instruct/FP8"},{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct-GGUF","kind":"Instruct/GGUF"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Next-80B-A3B-Instruct","u":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-next-80b-a3b-instruct"},{"id":"qwen3-next-80b-a3b-thinking","name":"Qwen3-Next-80B-A3B-Thinking","hf":"Qwen/Qwen3-Next-80B-A3B-Thinking","org":"Qwen","family":"qwen","series":"Qwen3-Next-Thinking","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-09-09","updated":"2025-09-15","gated":false,"params":{"total":81.325,"active":3,"src":"safetensors","q":null,"stTotal":81.325},"moe":true,"ctx":262144,"arch":{"L":48,"attn":12,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.2,"32768":0.81,"131072":3.22},"mem":{"bf16":{"w":162.65,"t":179.6},"fp8":{"w":86.41,"t":95.7},"q4":{"w":49.3,"t":54.9}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"h200","mac":"mac256"},"q4":{"gpu":"2x5090","mac":"mac128"}},"disk":162.66,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","kind":"main"},{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Next-80B-A3B-Thinking","u":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-next-80b-a3b-thinking"},{"id":"qwen3-omni-30b-a3b-instruct","name":"Qwen3-Omni-30B-A3B-Instruct","hf":"Qwen/Qwen3-Omni-30B-A3B-Instruct","org":"Qwen","family":"qwen","series":"Qwen3-Omni","task":"omni","pipeline":"any-to-any","tags":[],"released":"2025-09-20","updated":"2025-09-22","gated":false,"params":{"total":35.26,"active":3,"src":"safetensors","q":null,"stTotal":35.26},"moe":true,"ctx":65536,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22},"mem":{"bf16":{"w":70.52,"t":78.9},"fp8":{"w":37.46,"t":42.5},"q4":{"w":21.38,"t":24.8}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":70.52,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-Omni-30B-A3B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Omni-30B-A3B-Instruct","u":"https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-omni-30b-a3b-instruct"},{"id":"qwen3-omni-30b-a3b-thinking","name":"Qwen3-Omni-30B-A3B-Thinking","hf":"Qwen/Qwen3-Omni-30B-A3B-Thinking","org":"Qwen","family":"qwen","series":"Qwen3-Omni-Thinking","task":"omni","pipeline":"any-to-any","tags":["reasoning"],"released":"2025-09-15","updated":"2025-09-22","gated":false,"params":{"total":31.719,"active":3,"src":"safetensors","q":null,"stTotal":31.719},"moe":true,"ctx":65536,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22},"mem":{"bf16":{"w":63.44,"t":71.1},"fp8":{"w":33.7,"t":38.4},"q4":{"w":19.23,"t":22.5}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":63.44,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-Omni-30B-A3B-Thinking","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Omni-30B-A3B-Thinking","u":"https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Thinking"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Thinking/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-omni-30b-a3b-thinking"},{"id":"qwen3-reranker-0-6b","name":"Qwen3-Reranker-0.6B","hf":"Qwen/Qwen3-Reranker-0.6B","org":"Qwen","family":"qwen","series":"Qwen3-Reranker","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2025-05-29","updated":"2026-04-16","gated":false,"params":{"total":0.596,"active":null,"src":"safetensors","q":null,"stTotal":0.596},"moe":false,"ctx":40960,"arch":null,"kv":null,"mem":{"bf16":{"w":1.19,"t":1.8},"fp8":{"w":0.63,"t":1.2},"q4":{"w":0.36,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.19,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-Reranker-0.6B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Reranker-0.6B","u":"https://huggingface.co/Qwen/Qwen3-Reranker-0.6B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Reranker-0.6B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-reranker-0-6b"},{"id":"qwen3-reranker-4b","name":"Qwen3-Reranker-4B","hf":"Qwen/Qwen3-Reranker-4B","org":"Qwen","family":"qwen","series":"Qwen3-Reranker","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2025-06-03","updated":"2026-04-16","gated":false,"params":{"total":4.022,"active":null,"src":"safetensors","q":null,"stTotal":4.022},"moe":false,"ctx":40960,"arch":null,"kv":null,"mem":{"bf16":{"w":8.04,"t":9.3},"fp8":{"w":4.27,"t":5.2},"q4":{"w":2.44,"t":3.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.04,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-Reranker-4B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Reranker-4B","u":"https://huggingface.co/Qwen/Qwen3-Reranker-4B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Reranker-4B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-reranker-4b"},{"id":"qwen3-reranker-8b","name":"Qwen3-Reranker-8B","hf":"Qwen/Qwen3-Reranker-8B","org":"Qwen","family":"qwen","series":"Qwen3-Reranker","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2025-05-29","updated":"2026-04-16","gated":false,"params":{"total":8.189,"active":null,"src":"safetensors","q":null,"stTotal":8.189},"moe":false,"ctx":40960,"arch":null,"kv":null,"mem":{"bf16":{"w":16.38,"t":18.5},"fp8":{"w":8.7,"t":10.1},"q4":{"w":4.96,"t":6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.38,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-Reranker-8B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-Reranker-8B","u":"https://huggingface.co/Qwen/Qwen3-Reranker-8B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-Reranker-8B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-reranker-8b"},{"id":"qwen3-tts-12hz-0-6b-base","name":"Qwen3-TTS-12Hz-0.6B-Base","hf":"Qwen/Qwen3-TTS-12Hz-0.6B-Base","org":"Qwen","family":"qwen","series":"Qwen3-TTS-12Hz","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2026-01-21","updated":"2026-01-29","gated":false,"params":{"total":0.915,"active":null,"src":"safetensors","q":null,"stTotal":0.915},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.83,"t":2.5},"fp8":{"w":0.97,"t":1.6},"q4":{"w":0.55,"t":1.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.83,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"Qwen/Qwen3-TTS-12Hz-0.6B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-TTS-12Hz-0.6B-Base","u":"https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-tts-12hz-0-6b-base"},{"id":"qwen3-tts-12hz-1-7b-base","name":"Qwen3-TTS-12Hz-1.7B-Base","hf":"Qwen/Qwen3-TTS-12Hz-1.7B-Base","org":"Qwen","family":"qwen","series":"Qwen3-TTS-12Hz","task":"tts","pipeline":null,"tags":[],"released":"2026-01-21","updated":"2026-01-23","gated":false,"params":{"total":1.929,"active":null,"src":"safetensors","q":null,"stTotal":1.929},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":3.86,"t":4.7},"fp8":{"w":2.05,"t":2.8},"q4":{"w":1.17,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.86,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-TTS-12Hz-1.7B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-TTS-12Hz-1.7B-Base","u":"https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-tts-12hz-1-7b-base"},{"id":"qwen3-tts-12hz-0-6b-customvoice","name":"Qwen3-TTS-12Hz-0.6B-CustomVoice","hf":"Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice","org":"Qwen","family":"qwen","series":"Qwen3-TTS-12Hz-CustomVoice","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2026-01-21","updated":"2026-01-29","gated":false,"params":{"total":0.906,"active":null,"src":"safetensors","q":null,"stTotal":0.906},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.81,"t":2.5},"fp8":{"w":0.96,"t":1.6},"q4":{"w":0.55,"t":1.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.81,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice","u":"https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-tts-12hz-0-6b-customvoice"},{"id":"qwen3-tts-12hz-1-7b-customvoice","name":"Qwen3-TTS-12Hz-1.7B-CustomVoice","hf":"Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice","org":"Qwen","family":"qwen","series":"Qwen3-TTS-12Hz-CustomVoice","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2026-01-21","updated":"2026-01-29","gated":false,"params":{"total":1.917,"active":null,"src":"safetensors","q":null,"stTotal":1.917},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":3.83,"t":4.7},"fp8":{"w":2.04,"t":2.7},"q4":{"w":1.16,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.83,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice","u":"https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-tts-12hz-1-7b-customvoice"},{"id":"qwen3-tts-12hz-1-7b-voicedesign","name":"Qwen3-TTS-12Hz-1.7B-VoiceDesign","hf":"Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign","org":"Qwen","family":"qwen","series":"Qwen3-TTS-12Hz-VoiceDesign","task":"tts","pipeline":"text-to-speech","tags":[],"released":"2026-01-21","updated":"2026-01-29","gated":false,"params":{"total":1.917,"active":null,"src":"safetensors","q":null,"stTotal":1.917},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":3.83,"t":4.7},"fp8":{"w":2.04,"t":2.7},"q4":{"w":1.16,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.83,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign","u":"https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-tts-12hz-1-7b-voicedesign"},{"id":"qwen3-4b-thinking-2507","name":"Qwen3-4B-Thinking-2507","hf":"Qwen/Qwen3-4B-Thinking-2507","org":"Qwen","family":"qwen","series":"Qwen3-Thinking","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-08-05","updated":"2025-08-06","gated":false,"params":{"total":4.022,"active":null,"src":"safetensors","q":null,"stTotal":4.022},"moe":false,"ctx":262144,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83,"131072":19.33},"mem":{"bf16":{"w":8.04,"t":10.6},"fp8":{"w":4.27,"t":6.4},"q4":{"w":2.44,"t":4.4}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.04,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-4B-Thinking-2507","kind":"main"},{"id":"Qwen/Qwen3-4B-Thinking-2507-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-4B-Thinking-2507","u":"https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-4b-thinking-2507"},{"id":"qwen3-30b-a3b-thinking-2507","name":"Qwen3-30B-A3B-Thinking-2507","hf":"Qwen/Qwen3-30B-A3B-Thinking-2507","org":"Qwen","family":"qwen","series":"Qwen3-Thinking","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-07-29","updated":"2025-08-17","gated":false,"params":{"total":30.532,"active":3,"src":"safetensors","q":null,"stTotal":30.532},"moe":true,"ctx":262144,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22,"131072":12.88},"mem":{"bf16":{"w":61.06,"t":68.5},"fp8":{"w":32.44,"t":37},"q4":{"w":18.51,"t":21.7}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":61.07,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-30B-A3B-Thinking-2507","kind":"main"},{"id":"Qwen/Qwen3-30B-A3B-Thinking-2507-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-30B-A3B-Thinking-2507","u":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-30b-a3b-thinking-2507"},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen3-235B-A22B-Thinking-2507","hf":"Qwen/Qwen3-235B-A22B-Thinking-2507","org":"Qwen","family":"qwen","series":"Qwen3-Thinking","task":"llm","pipeline":"text-generation","tags":["reasoning"],"released":"2025-07-25","updated":"2025-08-17","gated":false,"params":{"total":235.094,"active":22,"src":"safetensors","q":null,"stTotal":235.094},"moe":true,"ctx":262144,"arch":{"L":94,"attn":94,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.58,"32768":6.31,"131072":25.23},"mem":{"bf16":{"w":470.19,"t":519.3},"fp8":{"w":249.79,"t":276.8},"q4":{"w":142.53,"t":158.9}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":470.19,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"ollama","via":"card"},{"id":"lmstudio","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-235B-A22B-Thinking-2507","u":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/qwen3-235b-a22b-thinking-2507/"},{"id":"qwen3-vl-2b-instruct","name":"Qwen3-VL-2B-Instruct","hf":"Qwen/Qwen3-VL-2B-Instruct","org":"Qwen","family":"qwen","series":"Qwen3-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-10-19","updated":"2025-10-23","gated":false,"params":{"total":2.128,"active":null,"src":"safetensors","q":null,"stTotal":2.128},"moe":false,"ctx":262144,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.94,"32768":3.76,"131072":15.03},"mem":{"bf16":{"w":4.26,"t":6.1},"fp8":{"w":2.26,"t":3.9},"q4":{"w":1.29,"t":2.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.26,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen3-vl:2b","url":"https://ollama.com/library/qwen3-vl"}],"variants":[{"id":"Qwen/Qwen3-VL-2B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen3-VL-2B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen3-VL-2B-Instruct-FP8","kind":"Instruct/FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-2B-Instruct","u":"https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct/blob/main/config.json"},{"t":"Ollama library · qwen3-vl","u":"https://ollama.com/library/qwen3-vl"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-2b-instruct"},{"id":"qwen3-vl-4b-instruct","name":"Qwen3-VL-4B-Instruct","hf":"Qwen/Qwen3-VL-4B-Instruct","org":"Qwen","family":"qwen","series":"Qwen3-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-10-11","updated":"2025-10-15","gated":false,"params":{"total":4.438,"active":null,"src":"safetensors","q":null,"stTotal":4.438},"moe":false,"ctx":262144,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83,"131072":19.33},"mem":{"bf16":{"w":8.88,"t":11.5},"fp8":{"w":4.72,"t":6.9},"q4":{"w":2.69,"t":4.7}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.88,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen3-vl:4b","url":"https://ollama.com/library/qwen3-vl"}],"variants":[{"id":"Qwen/Qwen3-VL-4B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen3-VL-4B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"Qwen/Qwen3-VL-4B-Instruct-FP8","kind":"Instruct/FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-4B-Instruct","u":"https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct/blob/main/config.json"},{"t":"Ollama library · qwen3-vl","u":"https://ollama.com/library/qwen3-vl"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-4b-instruct"},{"id":"qwen3-vl-8b-instruct","name":"Qwen3-VL-8B-Instruct","hf":"Qwen/Qwen3-VL-8B-Instruct","org":"Qwen","family":"qwen","series":"Qwen3-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-10-11","updated":"2025-10-15","gated":false,"params":{"total":8.767,"active":null,"src":"safetensors","q":null,"stTotal":8.767},"moe":false,"ctx":262144,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83,"131072":19.33},"mem":{"bf16":{"w":17.53,"t":21},"fp8":{"w":9.31,"t":12},"q4":{"w":5.31,"t":7.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":17.53,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen3-vl:8b","url":"https://ollama.com/library/qwen3-vl"}],"variants":[{"id":"Qwen/Qwen3-VL-8B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen3-VL-8B-Instruct-FP8","kind":"Instruct/FP8"},{"id":"Qwen/Qwen3-VL-8B-Instruct-GGUF","kind":"Instruct/GGUF"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-8B-Instruct","u":"https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct/blob/main/config.json"},{"t":"Ollama library · qwen3-vl","u":"https://ollama.com/library/qwen3-vl"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-8b-instruct"},{"id":"qwen3-vl-30b-a3b-instruct","name":"Qwen3-VL-30B-A3B-Instruct","hf":"Qwen/Qwen3-VL-30B-A3B-Instruct","org":"Qwen","family":"qwen","series":"Qwen3-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-09-30","updated":"2025-11-26","gated":false,"params":{"total":31.071,"active":3,"src":"safetensors","q":null,"stTotal":31.071},"moe":true,"ctx":262144,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22,"131072":12.88},"mem":{"bf16":{"w":62.14,"t":69.7},"fp8":{"w":33.01,"t":37.6},"q4":{"w":18.84,"t":22}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":62.14,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen3-vl:30b-a3b","url":"https://ollama.com/library/qwen3-vl"}],"variants":[{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct-FP8","kind":"Instruct/FP8"},{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct-GGUF","kind":"Instruct/GGUF"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-30B-A3B-Instruct","u":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct/blob/main/config.json"},{"t":"Ollama library · qwen3-vl","u":"https://ollama.com/library/qwen3-vl"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-30b-a3b-instruct"},{"id":"qwen3-vl-32b-instruct","name":"Qwen3-VL-32B-Instruct","hf":"Qwen/Qwen3-VL-32B-Instruct","org":"Qwen","family":"qwen","series":"Qwen3-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-10-19","updated":"2025-10-21","gated":false,"params":{"total":33.357,"active":null,"src":"safetensors","q":null,"stTotal":33.357},"moe":false,"ctx":262144,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59,"131072":34.36},"mem":{"bf16":{"w":66.71,"t":76},"fp8":{"w":35.44,"t":41.6},"q4":{"w":20.22,"t":24.9}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":66.71,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen3-vl:32b","url":"https://ollama.com/library/qwen3-vl"}],"variants":[{"id":"Qwen/Qwen3-VL-32B-Instruct-FP8","kind":"Instruct/FP8"},{"id":"Qwen/Qwen3-VL-32B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen3-VL-32B-Instruct-GGUF","kind":"Instruct/GGUF"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-32B-Instruct","u":"https://huggingface.co/Qwen/Qwen3-VL-32B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-32B-Instruct/blob/main/config.json"},{"t":"Ollama library · qwen3-vl","u":"https://ollama.com/library/qwen3-vl"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-32b-instruct"},{"id":"qwen3-vl-235b-a22b-instruct","name":"Qwen3-VL-235B-A22B-Instruct","hf":"Qwen/Qwen3-VL-235B-A22B-Instruct","org":"Qwen","family":"qwen","series":"Qwen3-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-09-22","updated":"2025-11-26","gated":false,"params":{"total":235.67,"active":22,"src":"safetensors","q":null,"stTotal":235.67},"moe":true,"ctx":262144,"arch":{"L":94,"attn":94,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.58,"32768":6.31,"131072":25.23},"mem":{"bf16":{"w":471.34,"t":520.6},"fp8":{"w":250.4,"t":277.5},"q4":{"w":142.87,"t":159.2}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":471.34,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"qwen3-vl:235b-a22b","url":"https://ollama.com/library/qwen3-vl"}],"variants":[{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","kind":"Instruct"},{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","kind":"Instruct/FP8"},{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct-GGUF","kind":"Instruct/GGUF"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-235B-A22B-Instruct","u":"https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct/blob/main/config.json"},{"t":"Ollama library · qwen3-vl","u":"https://ollama.com/library/qwen3-vl"}],"page":"https://aimap.page/en/models/compute/open-models/qwen3-vl-235b-a22b-instruct/"},{"id":"qwen3-vl-embedding-2b","name":"Qwen3-VL-Embedding-2B","hf":"Qwen/Qwen3-VL-Embedding-2B","org":"Qwen","family":"qwen","series":"Qwen3-VL-Embedding","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2026-01-07","updated":"2026-04-16","gated":false,"params":{"total":2.128,"active":null,"src":"safetensors","q":null,"stTotal":2.128},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":4.26,"t":5.2},"fp8":{"w":2.26,"t":3},"q4":{"w":1.29,"t":1.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.26,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-VL-Embedding-2B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-Embedding-2B","u":"https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-embedding-2b"},{"id":"qwen3-vl-embedding-8b","name":"Qwen3-VL-Embedding-8B","hf":"Qwen/Qwen3-VL-Embedding-8B","org":"Qwen","family":"qwen","series":"Qwen3-VL-Embedding","task":"embedding","pipeline":"sentence-similarity","tags":[],"released":"2026-01-07","updated":"2026-04-16","gated":false,"params":{"total":8.145,"active":null,"src":"safetensors","q":null,"stTotal":8.145},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":16.29,"t":18.4},"fp8":{"w":8.65,"t":10},"q4":{"w":4.94,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.29,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-VL-Embedding-8B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-Embedding-8B","u":"https://huggingface.co/Qwen/Qwen3-VL-Embedding-8B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-Embedding-8B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-embedding-8b"},{"id":"qwen3-vl-reranker-2b","name":"Qwen3-VL-Reranker-2B","hf":"Qwen/Qwen3-VL-Reranker-2B","org":"Qwen","family":"qwen","series":"Qwen3-VL-Reranker","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2026-01-07","updated":"2026-04-16","gated":false,"params":{"total":2.128,"active":null,"src":"safetensors","q":null,"stTotal":2.128},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":4.26,"t":5.2},"fp8":{"w":2.26,"t":3},"q4":{"w":1.29,"t":1.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.26,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-VL-Reranker-2B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-Reranker-2B","u":"https://huggingface.co/Qwen/Qwen3-VL-Reranker-2B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-Reranker-2B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-reranker-2b"},{"id":"qwen3-vl-reranker-8b","name":"Qwen3-VL-Reranker-8B","hf":"Qwen/Qwen3-VL-Reranker-8B","org":"Qwen","family":"qwen","series":"Qwen3-VL-Reranker","task":"rerank","pipeline":"text-ranking","tags":[],"released":"2026-01-07","updated":"2026-04-16","gated":false,"params":{"total":8.767,"active":null,"src":"safetensors","q":null,"stTotal":8.767},"moe":false,"ctx":262144,"arch":null,"kv":null,"mem":{"bf16":{"w":17.53,"t":19.8},"fp8":{"w":9.31,"t":10.7},"q4":{"w":5.31,"t":6.3}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.53,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"},{"id":"sentence-transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3-VL-Reranker-8B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-Reranker-8B","u":"https://huggingface.co/Qwen/Qwen3-VL-Reranker-8B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-Reranker-8B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-reranker-8b"},{"id":"qwen3-vl-2b-thinking","name":"Qwen3-VL-2B-Thinking","hf":"Qwen/Qwen3-VL-2B-Thinking","org":"Qwen","family":"qwen","series":"Qwen3-VL-Thinking","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-10-19","updated":"2025-10-20","gated":false,"params":{"total":2.128,"active":null,"src":"safetensors","q":null,"stTotal":2.128},"moe":false,"ctx":262144,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.94,"32768":3.76,"131072":15.03},"mem":{"bf16":{"w":4.26,"t":6.1},"fp8":{"w":2.26,"t":3.9},"q4":{"w":1.29,"t":2.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.26,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"Qwen/Qwen3-VL-2B-Thinking","kind":"main"},{"id":"Qwen/Qwen3-VL-2B-Thinking-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-VL-2B-Thinking-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-2B-Thinking","u":"https://huggingface.co/Qwen/Qwen3-VL-2B-Thinking"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-2B-Thinking/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-2b-thinking"},{"id":"qwen3-vl-4b-thinking","name":"Qwen3-VL-4B-Thinking","hf":"Qwen/Qwen3-VL-4B-Thinking","org":"Qwen","family":"qwen","series":"Qwen3-VL-Thinking","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-10-11","updated":"2025-10-15","gated":false,"params":{"total":4.438,"active":null,"src":"safetensors","q":null,"stTotal":4.438},"moe":false,"ctx":262144,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83,"131072":19.33},"mem":{"bf16":{"w":8.88,"t":11.5},"fp8":{"w":4.72,"t":6.9},"q4":{"w":2.69,"t":4.7}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.88,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"Qwen/Qwen3-VL-4B-Thinking","kind":"main"},{"id":"Qwen/Qwen3-VL-4B-Thinking-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-VL-4B-Thinking-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-4B-Thinking","u":"https://huggingface.co/Qwen/Qwen3-VL-4B-Thinking"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-4B-Thinking/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-4b-thinking"},{"id":"qwen3-vl-8b-thinking","name":"Qwen3-VL-8B-Thinking","hf":"Qwen/Qwen3-VL-8B-Thinking","org":"Qwen","family":"qwen","series":"Qwen3-VL-Thinking","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-10-11","updated":"2025-11-26","gated":false,"params":{"total":8.767,"active":null,"src":"safetensors","q":null,"stTotal":8.767},"moe":false,"ctx":262144,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83,"131072":19.33},"mem":{"bf16":{"w":17.53,"t":21},"fp8":{"w":9.31,"t":12},"q4":{"w":5.31,"t":7.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":17.53,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"Qwen/Qwen3-VL-8B-Thinking","kind":"main"},{"id":"Qwen/Qwen3-VL-8B-Thinking-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-VL-8B-Thinking-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-8B-Thinking","u":"https://huggingface.co/Qwen/Qwen3-VL-8B-Thinking"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-8B-Thinking/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-8b-thinking"},{"id":"qwen3-vl-30b-a3b-thinking","name":"Qwen3-VL-30B-A3B-Thinking","hf":"Qwen/Qwen3-VL-30B-A3B-Thinking","org":"Qwen","family":"qwen","series":"Qwen3-VL-Thinking","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-09-30","updated":"2025-11-26","gated":false,"params":{"total":31.071,"active":3,"src":"safetensors","q":null,"stTotal":31.071},"moe":true,"ctx":262144,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22,"131072":12.88},"mem":{"bf16":{"w":62.14,"t":69.7},"fp8":{"w":33.01,"t":37.6},"q4":{"w":18.84,"t":22}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":62.14,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"Qwen/Qwen3-VL-30B-A3B-Thinking","kind":"main"},{"id":"Qwen/Qwen3-VL-30B-A3B-Thinking-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-VL-30B-A3B-Thinking-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-30B-A3B-Thinking","u":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Thinking"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Thinking/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-30b-a3b-thinking"},{"id":"qwen3-vl-32b-thinking","name":"Qwen3-VL-32B-Thinking","hf":"Qwen/Qwen3-VL-32B-Thinking","org":"Qwen","family":"qwen","series":"Qwen3-VL-Thinking","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-10-19","updated":"2025-10-21","gated":false,"params":{"total":33.357,"active":null,"src":"safetensors","q":null,"stTotal":33.357},"moe":false,"ctx":262144,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59,"131072":34.36},"mem":{"bf16":{"w":66.71,"t":76},"fp8":{"w":35.44,"t":41.6},"q4":{"w":20.22,"t":24.9}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":66.71,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"Qwen/Qwen3-VL-32B-Thinking-FP8","kind":"FP8"},{"id":"Qwen/Qwen3-VL-32B-Thinking","kind":"main"},{"id":"Qwen/Qwen3-VL-32B-Thinking-GGUF","kind":"GGUF"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-32B-Thinking","u":"https://huggingface.co/Qwen/Qwen3-VL-32B-Thinking"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-32B-Thinking/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-vl-32b-thinking"},{"id":"qwen3-vl-235b-a22b-thinking","name":"Qwen3-VL-235B-A22B-Thinking","hf":"Qwen/Qwen3-VL-235B-A22B-Thinking","org":"Qwen","family":"qwen","series":"Qwen3-VL-Thinking","task":"vlm","pipeline":"image-text-to-text","tags":["reasoning"],"released":"2025-09-22","updated":"2025-11-26","gated":false,"params":{"total":235.67,"active":22,"src":"safetensors","q":null,"stTotal":235.67},"moe":true,"ctx":262144,"arch":{"L":94,"attn":94,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.58,"32768":6.31,"131072":25.23},"mem":{"bf16":{"w":471.34,"t":520.6},"fp8":{"w":250.4,"t":277.5},"q4":{"w":142.87,"t":159.2}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":471.34,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"}],"variants":[{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","kind":"main"},{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking-GGUF","kind":"GGUF"},{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3-VL-235B-A22B-Thinking","u":"https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Thinking"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Thinking/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/qwen3-vl-235b-a22b-thinking/"},{"id":"qwen3-5-0-8b","name":"Qwen3.5-0.8B","hf":"Qwen/Qwen3.5-0.8B","org":"Qwen","family":"qwen","series":"Qwen3.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-02-28","updated":"2026-03-02","gated":false,"params":{"total":0.873,"active":null,"src":"safetensors","q":null,"stTotal":0.873},"moe":false,"ctx":262144,"arch":{"L":24,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4,"131072":1.61},"mem":{"bf16":{"w":1.75,"t":2.5},"fp8":{"w":0.93,"t":1.6},"q4":{"w":0.53,"t":1.2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.75,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3.5-0.8B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3.5:0.8b","url":"https://ollama.com/library/qwen3.5"}],"variants":[{"id":"Qwen/Qwen3.5-0.8B","kind":"main"},{"id":"Qwen/Qwen3.5-0.8B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.5-0.8B","u":"https://huggingface.co/Qwen/Qwen3.5-0.8B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.5-0.8B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.5-0.8B/blob/main/LICENSE"},{"t":"Ollama library · qwen3.5","u":"https://ollama.com/library/qwen3.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-5-0-8b"},{"id":"qwen3-5-2b","name":"Qwen3.5-2B","hf":"Qwen/Qwen3.5-2B","org":"Qwen","family":"qwen","series":"Qwen3.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-02-28","updated":"2026-03-02","gated":false,"params":{"total":2.274,"active":null,"src":"safetensors","q":null,"stTotal":2.274},"moe":false,"ctx":262144,"arch":{"L":24,"attn":6,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.1,"32768":0.4,"131072":1.61},"mem":{"bf16":{"w":4.55,"t":5.6},"fp8":{"w":2.42,"t":3.3},"q4":{"w":1.38,"t":2.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.55,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3.5-2B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3.5:2b","url":"https://ollama.com/library/qwen3.5"}],"variants":[{"id":"Qwen/Qwen3.5-2B","kind":"main"},{"id":"Qwen/Qwen3.5-2B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.5-2B","u":"https://huggingface.co/Qwen/Qwen3.5-2B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.5-2B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.5-2B/blob/main/LICENSE"},{"t":"Ollama library · qwen3.5","u":"https://ollama.com/library/qwen3.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-5-2b"},{"id":"qwen3-5-4b","name":"Qwen3.5-4B","hf":"Qwen/Qwen3.5-4B","org":"Qwen","family":"qwen","series":"Qwen3.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-02-27","updated":"2026-03-02","gated":false,"params":{"total":4.66,"active":null,"src":"safetensors","q":null,"stTotal":4.66},"moe":false,"ctx":262144,"arch":{"L":32,"attn":8,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.27,"32768":1.07,"131072":4.29},"mem":{"bf16":{"w":9.32,"t":11},"fp8":{"w":4.95,"t":6.2},"q4":{"w":2.83,"t":3.9}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":9.32,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3.5-4B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3.5:4b","url":"https://ollama.com/library/qwen3.5"}],"variants":[{"id":"Qwen/Qwen3.5-4B","kind":"main"},{"id":"Qwen/Qwen3.5-4B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.5-4B","u":"https://huggingface.co/Qwen/Qwen3.5-4B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.5-4B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.5-4B/blob/main/LICENSE"},{"t":"Ollama library · qwen3.5","u":"https://ollama.com/library/qwen3.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-5-4b"},{"id":"qwen3-5-9b","name":"Qwen3.5-9B","hf":"Qwen/Qwen3.5-9B","org":"Qwen","family":"qwen","series":"Qwen3.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-02-27","updated":"2026-03-02","gated":false,"params":{"total":9.653,"active":null,"src":"safetensors","q":null,"stTotal":9.653},"moe":false,"ctx":262144,"arch":{"L":32,"attn":8,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.27,"32768":1.07,"131072":4.29},"mem":{"bf16":{"w":19.31,"t":22},"fp8":{"w":10.26,"t":12.1},"q4":{"w":5.85,"t":7.2}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":19.31,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3.5:9b","url":"https://ollama.com/library/qwen3.5"}],"variants":[{"id":"Qwen/Qwen3.5-9B","kind":"main"},{"id":"Qwen/Qwen3.5-9B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.5-9B","u":"https://huggingface.co/Qwen/Qwen3.5-9B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/LICENSE"},{"t":"Ollama library · qwen3.5","u":"https://ollama.com/library/qwen3.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-5-9b"},{"id":"qwen3-5-27b","name":"Qwen3.5-27B","hf":"Qwen/Qwen3.5-27B","org":"Qwen","family":"qwen","series":"Qwen3.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-02-24","updated":"2026-04-24","gated":false,"params":{"total":27.781,"active":null,"src":"safetensors","q":null,"stTotal":27.781},"moe":false,"ctx":262144,"arch":{"L":64,"attn":16,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.54,"32768":2.15,"131072":8.59},"mem":{"bf16":{"w":55.56,"t":62.2},"fp8":{"w":29.52,"t":33.5},"q4":{"w":16.84,"t":19.6}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":55.56,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3.5:27b","url":"https://ollama.com/library/qwen3.5"}],"variants":[{"id":"Qwen/Qwen3.5-27B","kind":"main"},{"id":"Qwen/Qwen3.5-27B-FP8","kind":"FP8"},{"id":"Qwen/Qwen3.5-27B-GPTQ-Int4","kind":"GPTQ/INT4"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.5-27B","u":"https://huggingface.co/Qwen/Qwen3.5-27B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/LICENSE"},{"t":"Ollama library · qwen3.5","u":"https://ollama.com/library/qwen3.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-5-27b"},{"id":"qwen3-5-35b-a3b","name":"Qwen3.5-35B-A3B","hf":"Qwen/Qwen3.5-35B-A3B","org":"Qwen","family":"qwen","series":"Qwen3.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-02-24","updated":"2026-04-24","gated":false,"params":{"total":35.952,"active":3,"src":"safetensors","q":null,"stTotal":35.952},"moe":true,"ctx":262144,"arch":{"L":40,"attn":10,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.17,"32768":0.67,"131072":2.68},"mem":{"bf16":{"w":71.9,"t":79.8},"fp8":{"w":38.2,"t":42.7},"q4":{"w":21.8,"t":24.6}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":71.9,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3.5:35b-a3b","url":"https://ollama.com/library/qwen3.5"}],"variants":[{"id":"Qwen/Qwen3.5-35B-A3B","kind":"main"},{"id":"Qwen/Qwen3.5-35B-A3B-FP8","kind":"FP8"},{"id":"Qwen/Qwen3.5-35B-A3B-GPTQ-Int4","kind":"GPTQ/INT4"},{"id":"Qwen/Qwen3.5-35B-A3B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.5-35B-A3B","u":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B/blob/main/LICENSE"},{"t":"Ollama library · qwen3.5","u":"https://ollama.com/library/qwen3.5"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-5-35b-a3b"},{"id":"qwen3-5-122b-a10b","name":"Qwen3.5-122B-A10B","hf":"Qwen/Qwen3.5-122B-A10B","org":"Qwen","family":"qwen","series":"Qwen3.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-02-24","updated":"2026-04-24","gated":false,"params":{"total":125.086,"active":10,"src":"safetensors","q":null,"stTotal":125.086},"moe":true,"ctx":262144,"arch":{"L":48,"attn":12,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.2,"32768":0.81,"131072":3.22},"mem":{"bf16":{"w":250.17,"t":275.9},"fp8":{"w":132.9,"t":146.9},"q4":{"w":75.83,"t":84.1}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac256"},"q4":{"gpu":"pro6000","mac":"mac128"}},"disk":250.17,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3.5:122b-a10b","url":"https://ollama.com/library/qwen3.5"}],"variants":[{"id":"Qwen/Qwen3.5-122B-A10B","kind":"main"},{"id":"Qwen/Qwen3.5-122B-A10B-GPTQ-Int4","kind":"GPTQ/INT4"},{"id":"Qwen/Qwen3.5-122B-A10B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.5-122B-A10B","u":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE"},{"t":"Ollama library · qwen3.5","u":"https://ollama.com/library/qwen3.5"}],"page":"https://aimap.page/en/models/compute/open-models/qwen3-5-122b-a10b/"},{"id":"qwen3-5-397b-a17b","name":"Qwen3.5-397B-A17B","hf":"Qwen/Qwen3.5-397B-A17B","org":"Qwen","family":"qwen","series":"Qwen3.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-02-16","updated":"2026-04-24","gated":false,"params":{"total":403.398,"active":17,"src":"safetensors","q":null,"stTotal":403.398},"moe":true,"ctx":262144,"arch":{"L":60,"attn":15,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.25,"32768":1.01,"131072":4.03},"mem":{"bf16":{"w":806.8,"t":888.2},"fp8":{"w":428.61,"t":472.2},"q4":{"w":244.56,"t":269.8}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":806.8,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3.5-397B-A17B","kind":"main"},{"id":"Qwen/Qwen3.5-397B-A17B-FP8","kind":"FP8"},{"id":"Qwen/Qwen3.5-397B-A17B-GPTQ-Int4","kind":"GPTQ/INT4"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.5-397B-A17B","u":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/qwen3-5-397b-a17b/"},{"id":"qwen3-6-27b","name":"Qwen3.6-27B","hf":"Qwen/Qwen3.6-27B","org":"Qwen","family":"qwen","series":"Qwen3.6","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-04-21","updated":"2026-04-24","gated":false,"params":{"total":27.781,"active":null,"src":"safetensors","q":null,"stTotal":27.781},"moe":false,"ctx":262144,"arch":{"L":64,"attn":16,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.54,"32768":2.15,"131072":8.59},"mem":{"bf16":{"w":55.56,"t":62.2},"fp8":{"w":29.52,"t":33.5},"q4":{"w":16.84,"t":19.6}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":55.56,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3.6:27b","url":"https://ollama.com/library/qwen3.6"}],"variants":[{"id":"Qwen/Qwen3.6-27B","kind":"main"},{"id":"Qwen/Qwen3.6-27B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.6-27B","u":"https://huggingface.co/Qwen/Qwen3.6-27B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE"},{"t":"Ollama library · qwen3.6","u":"https://ollama.com/library/qwen3.6"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-6-27b"},{"id":"qwen3-6-35b-a3b","name":"Qwen3.6-35B-A3B","hf":"Qwen/Qwen3.6-35B-A3B","org":"Qwen","family":"qwen","series":"Qwen3.6","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-04-15","updated":"2026-04-24","gated":false,"params":{"total":35.952,"active":3,"src":"safetensors","q":null,"stTotal":35.952},"moe":true,"ctx":262144,"arch":{"L":40,"attn":10,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.17,"32768":0.67,"131072":2.68},"mem":{"bf16":{"w":71.9,"t":79.8},"fp8":{"w":38.2,"t":42.7},"q4":{"w":21.8,"t":24.6}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":71.9,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3.6:35b-a3b","url":"https://ollama.com/library/qwen3.6"}],"variants":[{"id":"Qwen/Qwen3.6-35B-A3B","kind":"main"},{"id":"Qwen/Qwen3.6-35B-A3B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.6-35B-A3B","u":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE"},{"t":"Ollama library · qwen3.6","u":"https://ollama.com/library/qwen3.6"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-6-35b-a3b"},{"id":"qwen3-8-27b","name":"Qwen3.8-27B","hf":"Qwen/Qwen3.8-27B","org":"Qwen","family":"qwen","series":"Qwen3.8","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-08-05","updated":"2026-08-14","gated":false,"params":{"total":27.781,"active":null,"src":"safetensors","q":null,"stTotal":27.781},"moe":false,"ctx":262144,"arch":{"L":64,"attn":16,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.54,"32768":2.15,"131072":8.59},"mem":{"bf16":{"w":55.56,"t":62.2},"fp8":{"w":29.52,"t":33.5},"q4":{"w":16.84,"t":19.6}},"fits":{"bf16":{"gpu":"h100","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx4090","mac":"mac36"}},"disk":55.56,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3.8-27B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"qwen3.8:27b","url":"https://ollama.com/library/qwen3.8"}],"variants":[{"id":"Qwen/Qwen3.8-27B","kind":"main"},{"id":"Qwen/Qwen3.8-27B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.8-27B","u":"https://huggingface.co/Qwen/Qwen3.8-27B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.8-27B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.8-27B/blob/main/LICENSE"},{"t":"Ollama library · qwen3.8","u":"https://ollama.com/library/qwen3.8"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3-8-27b"},{"id":"qwen3-8-2-4t-a95b","name":"Qwen3.8-2.4T-A95B","hf":"Qwen/Qwen3.8-2.4T-A95B","org":"Qwen","family":"qwen","series":"Qwen3.8","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-08-08","updated":"2026-08-12","gated":false,"params":{"total":2400,"active":95,"src":"card","q":"Number of Parameters: 2.4T in total and 95B activated","stTotal":2446.183},"moe":true,"ctx":262144,"arch":{"L":92,"attn":23,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.77,"32768":3.09,"131072":12.35},"mem":{"bf16":{"w":4800,"t":5281.3},"fp8":{"w":2550,"t":2806.3},"q4":{"w":1455,"t":1601.8}},"fits":{"bf16":{"gpu":null,"mac":null},"fp8":{"gpu":"2x8xb300","mac":null},"q4":{"gpu":"8xb300","mac":null}},"disk":4892.37,"native":"BF16","license":{"id":"qwen3.8-max","name":"qwen3.8-max","link":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3.8-2.4T-A95B","kind":"main"},{"id":"Qwen/Qwen3.8-2.4T-A95B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.8-2.4T-A95B","u":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/qwen3-8-2-4t-a95b/"},{"id":"qwen3-8-flash-next","name":"Qwen3.8-Flash-Next","hf":"Qwen/Qwen3.8-Flash-Next","org":"Qwen","family":"qwen","series":"Qwen3.8-Flash-Next","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-08-24","updated":"2026-08-27","gated":false,"params":{"total":180,"active":6,"src":"card","q":"Number of Parameters: 125B with 6B activated, plus 51B n-gram embedding and 4B MTP","stTotal":180},"moe":true,"ctx":262144,"arch":{"L":48,"attn":12,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa+hybrid","exotic":[]},"kv":{"8192":0.2,"32768":0.81,"131072":3.22},"mem":{"bf16":{"w":360,"t":396.7},"fp8":{"w":191.25,"t":211.1},"q4":{"w":109.12,"t":120.7}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"h200","mac":"mac256"}},"disk":360,"native":"BF16","license":{"id":"qwen-community-1.0","name":"qwen-community-1.0","link":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next/blob/main/LICENSE","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"ktransformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3.8-Flash-Next","kind":"main"},{"id":"Qwen/Qwen3.8-Flash-Next-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3.8-Flash-Next","u":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/qwen3-8-flash-next/"},{"id":"qwen3guard-gen-0-6b","name":"Qwen3Guard-Gen-0.6B","hf":"Qwen/Qwen3Guard-Gen-0.6B","org":"Qwen","family":"qwen","series":"Qwen3Guard-Gen","task":"guard","pipeline":"text-generation","tags":[],"released":"2025-09-23","updated":"2025-11-07","gated":false,"params":{"total":0.752,"active":null,"src":"safetensors","q":null,"stTotal":0.752},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.94,"32768":3.76},"mem":{"bf16":{"w":1.5,"t":3.1},"fp8":{"w":0.8,"t":2.3},"q4":{"w":0.46,"t":1.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.5,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3Guard-Gen-0.6B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3Guard-Gen-0.6B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3Guard-Gen-0.6B","u":"https://huggingface.co/Qwen/Qwen3Guard-Gen-0.6B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3Guard-Gen-0.6B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3Guard-Gen-0.6B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3guard-gen-0-6b"},{"id":"qwen3guard-gen-4b","name":"Qwen3Guard-Gen-4B","hf":"Qwen/Qwen3Guard-Gen-4B","org":"Qwen","family":"qwen","series":"Qwen3Guard-Gen","task":"guard","pipeline":"text-generation","tags":[],"released":"2025-09-23","updated":"2025-11-07","gated":false,"params":{"total":4.411,"active":null,"src":"safetensors","q":null,"stTotal":4.411},"moe":false,"ctx":32768,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":8.82,"t":11.4},"fp8":{"w":4.69,"t":6.9},"q4":{"w":2.67,"t":4.7}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.82,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3Guard-Gen-4B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3Guard-Gen-4B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3Guard-Gen-4B","u":"https://huggingface.co/Qwen/Qwen3Guard-Gen-4B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3Guard-Gen-4B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3Guard-Gen-4B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3guard-gen-4b"},{"id":"qwen3guard-gen-8b","name":"Qwen3Guard-Gen-8B","hf":"Qwen/Qwen3Guard-Gen-8B","org":"Qwen","family":"qwen","series":"Qwen3Guard-Gen","task":"guard","pipeline":"text-generation","tags":[],"released":"2025-09-23","updated":"2025-11-07","gated":false,"params":{"total":8.191,"active":null,"src":"safetensors","q":null,"stTotal":8.191},"moe":false,"ctx":32768,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":16.38,"t":19.7},"fp8":{"w":8.7,"t":11.3},"q4":{"w":4.97,"t":7.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.38,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3Guard-Gen-8B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3Guard-Gen-8B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3Guard-Gen-8B","u":"https://huggingface.co/Qwen/Qwen3Guard-Gen-8B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3Guard-Gen-8B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3Guard-Gen-8B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3guard-gen-8b"},{"id":"qwen3guard-stream-0-6b","name":"Qwen3Guard-Stream-0.6B","hf":"Qwen/Qwen3Guard-Stream-0.6B","org":"Qwen","family":"qwen","series":"Qwen3Guard-Stream","task":"guard","pipeline":"feature-extraction","tags":[],"released":"2025-09-23","updated":"2026-09-27","gated":false,"params":{"total":0.597,"active":null,"src":"safetensors","q":null,"stTotal":0.597},"moe":false,"ctx":8192,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.94},"mem":{"bf16":{"w":1.19,"t":2.8},"fp8":{"w":0.63,"t":2.1},"q4":{"w":0.36,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.19,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Qwen/Qwen3Guard-Stream-0.6B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"Qwen/Qwen3Guard-Stream-0.6B","kind":"main"}],"sources":[{"t":"Hugging Face · Qwen/Qwen3Guard-Stream-0.6B","u":"https://huggingface.co/Qwen/Qwen3Guard-Stream-0.6B"},{"t":"config.json","u":"https://huggingface.co/Qwen/Qwen3Guard-Stream-0.6B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Qwen/Qwen3Guard-Stream-0.6B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/qwen/#m-qwen3guard-stream-0-6b"},{"id":"stable-audio-3-medium","name":"stable-audio-3-medium","hf":"stabilityai/stable-audio-3-medium","org":"stabilityai","family":"sd","series":"stable-audio-3-medium","task":"tts","pipeline":"text-to-audio","tags":[],"released":"2026-05-17","updated":"2026-10-06","gated":true,"params":{"total":2.305,"active":null,"src":"safetensors","q":null,"stTotal":2.305},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":4.61,"t":5.6},"fp8":{"w":2.45,"t":3.2},"q4":{"w":1.4,"t":2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":9.22,"native":"F32","license":{"id":"stable-audio-community","name":"stable-audio-community","link":"https://huggingface.co/stabilityai/stable-audio-3-medium/blob/main/LICENSE.md","cls":"cond"},"runtimes":[],"variants":[{"id":"stabilityai/stable-audio-3-medium","kind":"main"},{"id":"stabilityai/stable-audio-3-medium-base","kind":"Base"}],"sources":[{"t":"Hugging Face · stabilityai/stable-audio-3-medium","u":"https://huggingface.co/stabilityai/stable-audio-3-medium"},{"t":"License","u":"https://huggingface.co/stabilityai/stable-audio-3-medium/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/sd/#m-stable-audio-3-medium"},{"id":"stable-audio-3-small-music","name":"stable-audio-3-small-music","hf":"stabilityai/stable-audio-3-small-music","org":"stabilityai","family":"sd","series":"stable-audio-3-small-music","task":"tts","pipeline":"text-to-audio","tags":[],"released":"2026-05-17","updated":"2026-10-06","gated":true,"params":{"total":0.568,"active":null,"src":"safetensors","q":null,"stTotal":0.568},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.14,"t":1.7},"fp8":{"w":0.6,"t":1.2},"q4":{"w":0.34,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.27,"native":"F32","license":{"id":"stable-audio-community","name":"stable-audio-community","link":"https://huggingface.co/stabilityai/stable-audio-3-small-music/blob/main/LICENSE.md","cls":"cond"},"runtimes":[],"variants":[{"id":"stabilityai/stable-audio-3-small-music","kind":"main"},{"id":"stabilityai/stable-audio-3-small-music-base","kind":"Base"}],"sources":[{"t":"Hugging Face · stabilityai/stable-audio-3-small-music","u":"https://huggingface.co/stabilityai/stable-audio-3-small-music"},{"t":"License","u":"https://huggingface.co/stabilityai/stable-audio-3-small-music/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/sd/#m-stable-audio-3-small-music"},{"id":"stable-audio-3-small-sfx","name":"stable-audio-3-small-sfx","hf":"stabilityai/stable-audio-3-small-sfx","org":"stabilityai","family":"sd","series":"stable-audio-3-small-sfx","task":"tts","pipeline":"text-to-audio","tags":[],"released":"2026-05-17","updated":"2026-10-06","gated":true,"params":{"total":0.568,"active":null,"src":"safetensors","q":null,"stTotal":0.568},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.14,"t":1.7},"fp8":{"w":0.6,"t":1.2},"q4":{"w":0.34,"t":0.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.27,"native":"F32","license":{"id":"stable-audio-community","name":"stable-audio-community","link":"https://huggingface.co/stabilityai/stable-audio-3-small-sfx/blob/main/LICENSE.md","cls":"cond"},"runtimes":[],"variants":[{"id":"stabilityai/stable-audio-3-small-sfx","kind":"main"},{"id":"stabilityai/stable-audio-3-small-sfx-base","kind":"Base"}],"sources":[{"t":"Hugging Face · stabilityai/stable-audio-3-small-sfx","u":"https://huggingface.co/stabilityai/stable-audio-3-small-sfx"},{"t":"License","u":"https://huggingface.co/stabilityai/stable-audio-3-small-sfx/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/sd/#m-stable-audio-3-small-sfx"},{"id":"stable-audio-open-1-0","name":"stable-audio-open-1.0","hf":"stabilityai/stable-audio-open-1.0","org":"stabilityai","family":"sd","series":"stable-audio-open-1.0","task":"tts","pipeline":"text-to-audio","tags":[],"released":"2024-05-24","updated":"2025-06-19","gated":true,"params":{"total":1.213,"active":null,"src":"safetensors","q":null,"stTotal":1.213},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":2.43,"t":3.2},"fp8":{"w":1.29,"t":1.9},"q4":{"w":0.74,"t":1.3}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":4.85,"native":"F32","license":{"id":"stable-audio-community","name":"stable-audio-community","link":"https://huggingface.co/stabilityai/stable-audio-open-1.0/blob/main/LICENSE","cls":"cond"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"stabilityai/stable-audio-open-1.0","kind":"main"}],"sources":[{"t":"Hugging Face · stabilityai/stable-audio-open-1.0","u":"https://huggingface.co/stabilityai/stable-audio-open-1.0"},{"t":"License","u":"https://huggingface.co/stabilityai/stable-audio-open-1.0/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/sd/#m-stable-audio-open-1-0"},{"id":"stable-audio-open-small","name":"stable-audio-open-small","hf":"stabilityai/stable-audio-open-small","org":"stabilityai","family":"sd","series":"stable-audio-open-small","task":"tts","pipeline":"text-to-audio","tags":[],"released":"2025-05-12","updated":"2025-05-27","gated":true,"params":{"total":0.497,"active":null,"src":"safetensors","q":null,"stTotal":0.497},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":0.99,"t":1.6},"fp8":{"w":0.53,"t":1.1},"q4":{"w":0.3,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.68,"native":"F32","license":{"id":"stability-ai-community","name":"stability-ai-community","link":"https://huggingface.co/stabilityai/stable-audio-open-small/blob/main/LICENSE","cls":"cond"},"runtimes":[],"variants":[{"id":"stabilityai/stable-audio-open-small","kind":"main"}],"sources":[{"t":"Hugging Face · stabilityai/stable-audio-open-small","u":"https://huggingface.co/stabilityai/stable-audio-open-small"},{"t":"License","u":"https://huggingface.co/stabilityai/stable-audio-open-small/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/sd/#m-stable-audio-open-small"},{"id":"stable-diffusion-3-medium-diffusers","name":"stable-diffusion-3-medium-diffusers","hf":"stabilityai/stable-diffusion-3-medium-diffusers","org":"stabilityai","family":"sd","series":"stable-diffusion-3-medium","task":"image","pipeline":"text-to-image","tags":[],"released":"2024-06-12","updated":"2024-06-19","gated":true,"params":{"total":2.085,"active":null,"src":"safetensors","q":null,"stTotal":2.085},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":4.17,"t":5.1},"fp8":{"w":2.22,"t":2.9},"q4":{"w":1.26,"t":1.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":31,"native":"F16","license":{"id":"stabilityai-nc-research-community","name":"stabilityai-nc-research-community","link":"https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers/blob/main/LICENSE","cls":"nc"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"stabilityai/stable-diffusion-3-medium-diffusers","kind":"Diffusers"},{"id":"stabilityai/stable-diffusion-3-medium","kind":"main"},{"id":"stabilityai/stable-diffusion-3-medium_amdgpu","kind":"main"}],"sources":[{"t":"Hugging Face · stabilityai/stable-diffusion-3-medium-diffusers","u":"https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers"},{"t":"License","u":"https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/sd/#m-stable-diffusion-3-medium-diffusers"},{"id":"stable-diffusion-3-5-large","name":"stable-diffusion-3.5-large","hf":"stabilityai/stable-diffusion-3.5-large","org":"stabilityai","family":"sd","series":"stable-diffusion-3.5-large","task":"image","pipeline":"text-to-image","tags":[],"released":"2024-10-22","updated":"2024-10-22","gated":true,"params":{"total":8.146,"active":null,"src":"safetensors","q":null,"stTotal":8.146},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":16.29,"t":18.4},"fp8":{"w":8.66,"t":10},"q4":{"w":4.94,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.46,"native":"BF16","license":{"id":"stabilityai-ai-community","name":"stabilityai-ai-community","link":"https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/LICENSE.md","cls":"cond"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"stabilityai/stable-diffusion-3.5-large","kind":"main"},{"id":"stabilityai/stable-diffusion-3.5-large_amdgpu","kind":"main"}],"sources":[{"t":"Hugging Face · stabilityai/stable-diffusion-3.5-large","u":"https://huggingface.co/stabilityai/stable-diffusion-3.5-large"},{"t":"License","u":"https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/sd/#m-stable-diffusion-3-5-large"},{"id":"stable-diffusion-3-5-large-turbo","name":"stable-diffusion-3.5-large-turbo","hf":"stabilityai/stable-diffusion-3.5-large-turbo","org":"stabilityai","family":"sd","series":"stable-diffusion-3.5-large-turbo","task":"image","pipeline":"text-to-image","tags":[],"released":"2024-10-22","updated":"2024-10-22","gated":true,"params":{"total":8.146,"active":null,"src":"safetensors","q":null,"stTotal":8.146},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":16.29,"t":18.4},"fp8":{"w":8.66,"t":10},"q4":{"w":4.94,"t":5.9}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.46,"native":"BF16","license":{"id":"stabilityai-ai-community","name":"stabilityai-ai-community","link":"https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo/blob/main/LICENSE.md","cls":"cond"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"stabilityai/stable-diffusion-3.5-large-turbo","kind":"main"},{"id":"stabilityai/stable-diffusion-3.5-large-turbo_amdgpu","kind":"main"}],"sources":[{"t":"Hugging Face · stabilityai/stable-diffusion-3.5-large-turbo","u":"https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo"},{"t":"License","u":"https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/sd/#m-stable-diffusion-3-5-large-turbo"},{"id":"stable-diffusion-3-5-medium","name":"stable-diffusion-3.5-medium","hf":"stabilityai/stable-diffusion-3.5-medium","org":"stabilityai","family":"sd","series":"stable-diffusion-3.5-medium","task":"image","pipeline":"text-to-image","tags":[],"released":"2024-10-29","updated":"2024-10-31","gated":true,"params":{"total":2.47,"active":null,"src":"safetensors","q":null,"stTotal":2.47},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":4.94,"t":5.9},"fp8":{"w":2.62,"t":3.4},"q4":{"w":1.5,"t":2.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":5.11,"native":"BF16","license":{"id":"stabilityai-ai-community","name":"stabilityai-ai-community","link":"https://huggingface.co/stabilityai/stable-diffusion-3.5-medium/blob/main/LICENSE.md","cls":"cond"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"stabilityai/stable-diffusion-3.5-medium","kind":"main"},{"id":"stabilityai/stable-diffusion-3.5-medium_amdgpu","kind":"main"}],"sources":[{"t":"Hugging Face · stabilityai/stable-diffusion-3.5-medium","u":"https://huggingface.co/stabilityai/stable-diffusion-3.5-medium"},{"t":"License","u":"https://huggingface.co/stabilityai/stable-diffusion-3.5-medium/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/sd/#m-stable-diffusion-3-5-medium"},{"id":"sv4d2-0","name":"sv4d2.0","hf":"stabilityai/sv4d2.0","org":"stabilityai","family":"sd","series":"sv4d2.0","task":"llm","pipeline":null,"tags":[],"released":"2025-02-20","updated":"2025-04-04","gated":false,"params":{"total":null,"active":null,"src":null,"q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":null,"fits":null,"disk":23.96,"native":null,"license":{"id":"stabilityai-ai-community","name":"stabilityai-ai-community","link":"https://huggingface.co/stabilityai/sv4d2.0/blob/main/LICENSE.md","cls":"cond"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"stabilityai/sv4d2.0","kind":"main"}],"sources":[{"t":"Hugging Face · stabilityai/sv4d2.0","u":"https://huggingface.co/stabilityai/sv4d2.0"},{"t":"License","u":"https://huggingface.co/stabilityai/sv4d2.0/blob/main/LICENSE.md"}],"page":"https://aimap.page/en/models/compute/open-models/family/sd/#m-sv4d2-0"},{"id":"bagel-7b-mot","name":"BAGEL-7B-MoT","hf":"ByteDance-Seed/BAGEL-7B-MoT","org":"ByteDance-Seed","family":"seed","series":"BAGEL-MoT","task":"omni","pipeline":"any-to-any","tags":[],"released":"2025-05-19","updated":"2026-01-09","gated":false,"params":{"total":14.691,"active":null,"src":"safetensors","q":null,"stTotal":14.691},"moe":false,"ctx":32768,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":29.38,"t":33.3},"fp8":{"w":15.61,"t":18.1},"q4":{"w":8.91,"t":10.8}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac24"}},"disk":29.55,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"ByteDance-Seed/BAGEL-7B-MoT","kind":"main"}],"sources":[{"t":"Hugging Face · ByteDance-Seed/BAGEL-7B-MoT","u":"https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT"},{"t":"config.json","u":"https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/seed/#m-bagel-7b-mot"},{"id":"seed-coder-8b-instruct","name":"Seed-Coder-8B-Instruct","hf":"ByteDance-Seed/Seed-Coder-8B-Instruct","org":"ByteDance-Seed","family":"seed","series":"Seed-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2025-04-27","updated":"2025-06-06","gated":false,"params":{"total":8.25,"active":null,"src":"safetensors","q":null,"stTotal":8.25},"moe":false,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29},"mem":{"bf16":{"w":16.5,"t":19.7},"fp8":{"w":8.77,"t":11.2},"q4":{"w":5,"t":7.1}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.5,"native":"BF16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ByteDance-Seed/Seed-Coder-8B-Instruct","kind":"Instruct"},{"id":"ByteDance-Seed/Seed-Coder-8B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · ByteDance-Seed/Seed-Coder-8B-Instruct","u":"https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Instruct"},{"t":"config.json","u":"https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/seed/#m-seed-coder-8b-instruct"},{"id":"seed-oss-36b-instruct","name":"Seed-OSS-36B-Instruct","hf":"ByteDance-Seed/Seed-OSS-36B-Instruct","org":"ByteDance-Seed","family":"seed","series":"Seed-OSS","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-08-20","updated":"2025-08-26","gated":false,"params":{"total":36.151,"active":null,"src":"safetensors","q":null,"stTotal":36.151},"moe":false,"ctx":524288,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59,"131072":34.36},"mem":{"bf16":{"w":72.3,"t":82.2},"fp8":{"w":38.41,"t":44.9},"q4":{"w":21.92,"t":26.8}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac128"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":72.3,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct/blob/main/LICENSE.txt","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ByteDance-Seed/Seed-OSS-36B-Instruct","kind":"Instruct"},{"id":"ByteDance-Seed/Seed-OSS-36B-Base","kind":"Base"}],"sources":[{"t":"Hugging Face · ByteDance-Seed/Seed-OSS-36B-Instruct","u":"https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct"},{"t":"config.json","u":"https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/seed/#m-seed-oss-36b-instruct"},{"id":"seed-x-instruct-7b","name":"Seed-X-Instruct-7B","hf":"ByteDance-Seed/Seed-X-Instruct-7B","org":"ByteDance-Seed","family":"seed","series":"Seed-X","task":"translate","pipeline":"translation","tags":[],"released":"2025-07-16","updated":"2025-07-28","gated":false,"params":{"total":7.514,"active":null,"src":"safetensors","q":null,"stTotal":7.514},"moe":false,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29},"mem":{"bf16":{"w":15.03,"t":18.1},"fp8":{"w":7.98,"t":10.4},"q4":{"w":4.56,"t":6.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.03,"native":"BF16","license":{"id":"openmdw","name":"OpenMDW","link":"https://huggingface.co/ByteDance-Seed/Seed-X-Instruct-7B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ByteDance-Seed/Seed-X-Instruct-7B","kind":"Instruct"}],"sources":[{"t":"Hugging Face · ByteDance-Seed/Seed-X-Instruct-7B","u":"https://huggingface.co/ByteDance-Seed/Seed-X-Instruct-7B"},{"t":"config.json","u":"https://huggingface.co/ByteDance-Seed/Seed-X-Instruct-7B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/ByteDance-Seed/Seed-X-Instruct-7B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/seed/#m-seed-x-instruct-7b"},{"id":"seed-x-ppo-7b","name":"Seed-X-PPO-7B","hf":"ByteDance-Seed/Seed-X-PPO-7B","org":"ByteDance-Seed","family":"seed","series":"Seed-X-PPO","task":"translate","pipeline":"translation","tags":[],"released":"2025-07-16","updated":"2025-07-28","gated":false,"params":{"total":7.514,"active":null,"src":"safetensors","q":null,"stTotal":7.514},"moe":false,"ctx":32768,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.07,"32768":4.29},"mem":{"bf16":{"w":15.03,"t":18.1},"fp8":{"w":7.98,"t":10.4},"q4":{"w":4.56,"t":6.6}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":15.03,"native":"BF16","license":{"id":"openmdw","name":"OpenMDW","link":"https://huggingface.co/ByteDance-Seed/Seed-X-PPO-7B/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"ByteDance-Seed/Seed-X-PPO-7B","kind":"main"},{"id":"ByteDance-Seed/Seed-X-PPO-7B-GPTQ-Int8","kind":"GPTQ/INT8"},{"id":"ByteDance-Seed/Seed-X-PPO-7B-AWQ-Int4","kind":"AWQ/INT4"}],"sources":[{"t":"Hugging Face · ByteDance-Seed/Seed-X-PPO-7B","u":"https://huggingface.co/ByteDance-Seed/Seed-X-PPO-7B"},{"t":"config.json","u":"https://huggingface.co/ByteDance-Seed/Seed-X-PPO-7B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/ByteDance-Seed/Seed-X-PPO-7B/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/family/seed/#m-seed-x-ppo-7b"},{"id":"seedvr-3b","name":"SeedVR-3B","hf":"ByteDance-Seed/SeedVR-3B","org":"ByteDance-Seed","family":"seed","series":"SeedVR","task":"video","pipeline":"video-to-video","tags":[],"released":"2025-06-11","updated":"2025-06-20","gated":false,"params":{"total":3,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":6,"t":7.1},"fp8":{"w":3.19,"t":4},"q4":{"w":1.82,"t":2.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":14.57,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"ByteDance-Seed/SeedVR-3B","kind":"main"}],"sources":[{"t":"Hugging Face · ByteDance-Seed/SeedVR-3B","u":"https://huggingface.co/ByteDance-Seed/SeedVR-3B"}],"page":"https://aimap.page/en/models/compute/open-models/family/seed/#m-seedvr-3b"},{"id":"seedvr2-3b","name":"SeedVR2-3B","hf":"ByteDance-Seed/SeedVR2-3B","org":"ByteDance-Seed","family":"seed","series":"SeedVR2","task":"video","pipeline":"video-to-video","tags":[],"released":"2025-06-10","updated":"2025-06-22","gated":false,"params":{"total":3,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":6,"t":7.1},"fp8":{"w":3.19,"t":4},"q4":{"w":1.82,"t":2.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":14.57,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"ByteDance-Seed/SeedVR2-3B","kind":"main"}],"sources":[{"t":"Hugging Face · ByteDance-Seed/SeedVR2-3B","u":"https://huggingface.co/ByteDance-Seed/SeedVR2-3B"}],"page":"https://aimap.page/en/models/compute/open-models/family/seed/#m-seedvr2-3b"},{"id":"seedvr2-7b","name":"SeedVR2-7B","hf":"ByteDance-Seed/SeedVR2-7B","org":"ByteDance-Seed","family":"seed","series":"SeedVR2","task":"video","pipeline":"video-to-video","tags":[],"released":"2025-06-11","updated":"2025-07-14","gated":false,"params":{"total":7,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":14,"t":15.9},"fp8":{"w":7.44,"t":8.7},"q4":{"w":4.24,"t":5.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":66.92,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"ByteDance-Seed/SeedVR2-7B","kind":"main"}],"sources":[{"t":"Hugging Face · ByteDance-Seed/SeedVR2-7B","u":"https://huggingface.co/ByteDance-Seed/SeedVR2-7B"}],"page":"https://aimap.page/en/models/compute/open-models/family/seed/#m-seedvr2-7b"},{"id":"ui-tars-1-5-7b","name":"UI-TARS-1.5-7B","hf":"ByteDance-Seed/UI-TARS-1.5-7B","org":"ByteDance-Seed","family":"seed","series":"UI-TARS-1.5","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-04-16","updated":"2025-04-18","gated":false,"params":{"total":8.292,"active":null,"src":"safetensors","q":null,"stTotal":8.292},"moe":false,"ctx":128000,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47,"32768":1.88},"mem":{"bf16":{"w":16.58,"t":19.2},"fp8":{"w":8.81,"t":10.7},"q4":{"w":5.03,"t":6.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":33.17,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"ByteDance-Seed/UI-TARS-1.5-7B","kind":"main"}],"sources":[{"t":"Hugging Face · ByteDance-Seed/UI-TARS-1.5-7B","u":"https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B"},{"t":"config.json","u":"https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/seed/#m-ui-tars-1-5-7b"},{"id":"smollm-135m","name":"SmolLM-135M","hf":"HuggingFaceTB/SmolLM-135M","org":"HuggingFaceTB","family":"smollm","series":"SmolLM","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-07-14","updated":"2024-08-01","gated":false,"params":{"total":0.135,"active":null,"src":"safetensors","q":null,"stTotal":0.135},"moe":false,"ctx":2048,"arch":{"L":30,"attn":30,"slide":0,"win":null,"kvElems":384,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.19},"mem":{"bf16":{"w":0.27,"t":1},"fp8":{"w":0.14,"t":0.8},"q4":{"w":0.08,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.54,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"ollama","via":"ollama-library","tag":"smollm:135m","url":"https://ollama.com/library/smollm"}],"variants":[{"id":"HuggingFaceTB/SmolLM-135M","kind":"main"},{"id":"HuggingFaceTB/SmolLM-135M-Instruct","kind":"Instruct"},{"id":"HuggingFaceTB/smollm-135M-instruct-v0.2-Q8_0-GGUF","kind":"Instruct/GGUF"}],"sources":[{"t":"Hugging Face · HuggingFaceTB/SmolLM-135M","u":"https://huggingface.co/HuggingFaceTB/SmolLM-135M"},{"t":"config.json","u":"https://huggingface.co/HuggingFaceTB/SmolLM-135M/blob/main/config.json"},{"t":"Ollama library · smollm","u":"https://ollama.com/library/smollm"}],"page":"https://aimap.page/en/models/compute/open-models/family/smollm/#m-smollm-135m"},{"id":"smollm-360m","name":"SmolLM-360M","hf":"HuggingFaceTB/SmolLM-360M","org":"HuggingFaceTB","family":"smollm","series":"SmolLM","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-07-14","updated":"2024-08-01","gated":false,"params":{"total":0.362,"active":null,"src":"safetensors","q":null,"stTotal":0.362},"moe":false,"ctx":2048,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":640,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.34},"mem":{"bf16":{"w":0.72,"t":1.6},"fp8":{"w":0.38,"t":1.3},"q4":{"w":0.22,"t":1.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.45,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"smollm:360m","url":"https://ollama.com/library/smollm"}],"variants":[{"id":"HuggingFaceTB/SmolLM-360M","kind":"main"},{"id":"HuggingFaceTB/SmolLM-360M-Instruct","kind":"Instruct"},{"id":"HuggingFaceTB/SmolLM-360M-Instruct-ONNX-fp16","kind":"Instruct/ONNX/FP16"},{"id":"HuggingFaceTB/smollm-360M-instruct-add-basics","kind":"Instruct"}],"sources":[{"t":"Hugging Face · HuggingFaceTB/SmolLM-360M","u":"https://huggingface.co/HuggingFaceTB/SmolLM-360M"},{"t":"config.json","u":"https://huggingface.co/HuggingFaceTB/SmolLM-360M/blob/main/config.json"},{"t":"Ollama library · smollm","u":"https://ollama.com/library/smollm"}],"page":"https://aimap.page/en/models/compute/open-models/family/smollm/#m-smollm-360m"},{"id":"smollm-1-7b","name":"SmolLM-1.7B","hf":"HuggingFaceTB/SmolLM-1.7B","org":"HuggingFaceTB","family":"smollm","series":"SmolLM","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-07-14","updated":"2024-10-16","gated":false,"params":{"total":1.711,"active":null,"src":"safetensors","q":null,"stTotal":1.711},"moe":false,"ctx":2048,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.61},"mem":{"bf16":{"w":3.42,"t":5.9},"fp8":{"w":1.82,"t":4.1},"q4":{"w":1.04,"t":3.3}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.85,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"smollm:1.7b","url":"https://ollama.com/library/smollm"}],"variants":[{"id":"HuggingFaceTB/SmolLM-1.7B","kind":"main"},{"id":"HuggingFaceTB/SmolLM-1.7B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · HuggingFaceTB/SmolLM-1.7B","u":"https://huggingface.co/HuggingFaceTB/SmolLM-1.7B"},{"t":"config.json","u":"https://huggingface.co/HuggingFaceTB/SmolLM-1.7B/blob/main/config.json"},{"t":"Ollama library · smollm","u":"https://ollama.com/library/smollm"}],"page":"https://aimap.page/en/models/compute/open-models/family/smollm/#m-smollm-1-7b"},{"id":"smollm2-135m","name":"SmolLM2-135M","hf":"HuggingFaceTB/SmolLM2-135M","org":"HuggingFaceTB","family":"smollm","series":"SmolLM2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-10-31","updated":"2025-02-06","gated":false,"params":{"total":0.135,"active":null,"src":"safetensors","q":null,"stTotal":0.135},"moe":false,"ctx":8192,"arch":{"L":30,"attn":30,"slide":0,"win":null,"kvElems":384,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.19},"mem":{"bf16":{"w":0.27,"t":1},"fp8":{"w":0.14,"t":0.8},"q4":{"w":0.08,"t":0.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.27,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"mlx","via":"official-mlx"},{"id":"ollama","via":"ollama-library","tag":"smollm2:135m","url":"https://ollama.com/library/smollm2"}],"variants":[{"id":"HuggingFaceTB/SmolLM2-135M","kind":"main"},{"id":"HuggingFaceTB/SmolLM2-135M-Instruct","kind":"Instruct"},{"id":"HuggingFaceTB/SmolVLM-256M-Instruct","kind":"Instruct"},{"id":"HuggingFaceTB/SmolLM2-135M-Instruct-Q8-mlx","kind":"Instruct/MLX"}],"sources":[{"t":"Hugging Face · HuggingFaceTB/SmolLM2-135M","u":"https://huggingface.co/HuggingFaceTB/SmolLM2-135M"},{"t":"config.json","u":"https://huggingface.co/HuggingFaceTB/SmolLM2-135M/blob/main/config.json"},{"t":"Ollama library · smollm2","u":"https://ollama.com/library/smollm2"}],"page":"https://aimap.page/en/models/compute/open-models/family/smollm/#m-smollm2-135m"},{"id":"smollm2-360m","name":"SmolLM2-360M","hf":"HuggingFaceTB/SmolLM2-360M","org":"HuggingFaceTB","family":"smollm","series":"SmolLM2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-10-31","updated":"2025-02-06","gated":false,"params":{"total":0.362,"active":null,"src":"safetensors","q":null,"stTotal":0.362},"moe":false,"ctx":8192,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":640,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.34},"mem":{"bf16":{"w":0.72,"t":1.6},"fp8":{"w":0.38,"t":1.3},"q4":{"w":0.22,"t":1.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":0.72,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"},{"id":"ollama","via":"ollama-library","tag":"smollm2:360m","url":"https://ollama.com/library/smollm2"}],"variants":[{"id":"HuggingFaceTB/SmolLM2-360M-Instruct","kind":"Instruct"},{"id":"HuggingFaceTB/SmolLM2-360M","kind":"main"},{"id":"HuggingFaceTB/SmolVLM-500M-Instruct","kind":"Instruct"},{"id":"HuggingFaceTB/SmolLM2-360M-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"HuggingFaceTB/SmolLM2-360M-Instruct-Q8-mlx","kind":"Instruct/MLX"}],"sources":[{"t":"Hugging Face · HuggingFaceTB/SmolLM2-360M","u":"https://huggingface.co/HuggingFaceTB/SmolLM2-360M"},{"t":"config.json","u":"https://huggingface.co/HuggingFaceTB/SmolLM2-360M/blob/main/config.json"},{"t":"Ollama library · smollm2","u":"https://ollama.com/library/smollm2"}],"page":"https://aimap.page/en/models/compute/open-models/family/smollm/#m-smollm2-360m"},{"id":"smollm2-1-7b","name":"SmolLM2-1.7B","hf":"HuggingFaceTB/SmolLM2-1.7B","org":"HuggingFaceTB","family":"smollm","series":"SmolLM2","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-10-30","updated":"2025-02-06","gated":false,"params":{"total":1.711,"active":null,"src":"safetensors","q":null,"stTotal":1.711},"moe":false,"ctx":8192,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.61},"mem":{"bf16":{"w":3.42,"t":5.9},"fp8":{"w":1.82,"t":4.1},"q4":{"w":1.04,"t":3.3}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":3.42,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"llamacpp","via":"official-gguf"},{"id":"mlx","via":"official-mlx"},{"id":"ollama","via":"ollama-library","tag":"smollm2:1.7b","url":"https://ollama.com/library/smollm2"}],"variants":[{"id":"HuggingFaceTB/SmolLM2-1.7B-Instruct","kind":"Instruct"},{"id":"HuggingFaceTB/SmolLM2-1.7B","kind":"main"},{"id":"HuggingFaceTB/SmolVLM-Instruct","kind":"Instruct"},{"id":"HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF","kind":"Instruct/GGUF"},{"id":"HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx","kind":"Instruct/MLX"}],"sources":[{"t":"Hugging Face · HuggingFaceTB/SmolLM2-1.7B","u":"https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B"},{"t":"config.json","u":"https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B/blob/main/config.json"},{"t":"Ollama library · smollm2","u":"https://ollama.com/library/smollm2"}],"page":"https://aimap.page/en/models/compute/open-models/family/smollm/#m-smollm2-1-7b"},{"id":"smollm3-3b","name":"SmolLM3-3B","hf":"HuggingFaceTB/SmolLM3-3B","org":"HuggingFaceTB","family":"smollm","series":"SmolLM3","task":"llm","pipeline":"text-generation","tags":[],"released":"2025-07-08","updated":"2025-09-10","gated":false,"params":{"total":3.075,"active":null,"src":"safetensors","q":null,"stTotal":3.075},"moe":false,"ctx":65536,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.6,"32768":2.42},"mem":{"bf16":{"w":6.15,"t":7.9},"fp8":{"w":3.27,"t":4.7},"q4":{"w":1.86,"t":3.2}},"fits":{"bf16":{"gpu":"gpu12","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":6.15,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"mlx","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"HuggingFaceTB/SmolLM3-3B","kind":"main"},{"id":"HuggingFaceTB/SmolLM3-3B-Base","kind":"Base"},{"id":"HuggingFaceTB/SmolLM3-3B-ONNX","kind":"ONNX"}],"sources":[{"t":"Hugging Face · HuggingFaceTB/SmolLM3-3B","u":"https://huggingface.co/HuggingFaceTB/SmolLM3-3B"},{"t":"config.json","u":"https://huggingface.co/HuggingFaceTB/SmolLM3-3B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/smollm/#m-smollm3-3b"},{"id":"smolvlm2-2-2b-instruct","name":"SmolVLM2-2.2B-Instruct","hf":"HuggingFaceTB/SmolVLM2-2.2B-Instruct","org":"HuggingFaceTB","family":"smollm","series":"SmolVLM2","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-02-08","updated":"2025-04-08","gated":false,"params":{"total":2.247,"active":null,"src":"safetensors","q":null,"stTotal":2.247},"moe":false,"ctx":8192,"arch":{"L":24,"attn":null,"slide":null,"win":null,"kvElems":null,"kvMethod":null,"exotic":[]},"kv":null,"mem":{"bf16":{"w":4.49,"t":5.4},"fp8":{"w":2.39,"t":3.1},"q4":{"w":1.36,"t":2}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":8.99,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"HuggingFaceTB/SmolVLM2-2.2B-Instruct","kind":"Instruct"}],"sources":[{"t":"Hugging Face · HuggingFaceTB/SmolVLM2-2.2B-Instruct","u":"https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct"},{"t":"config.json","u":"https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/smollm/#m-smolvlm2-2-2b-instruct"},{"id":"got-ocr-2-0-hf","name":"GOT-OCR-2.0-hf","hf":"stepfun-ai/GOT-OCR-2.0-hf","org":"stepfun-ai","family":"step","series":"GOT-OCR-2.0","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2024-11-22","updated":"2025-01-31","gated":false,"params":{"total":0.561,"active":null,"src":"safetensors","q":null,"stTotal":0.561},"moe":false,"ctx":null,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22,"131072":12.88},"mem":{"bf16":{"w":1.12,"t":2.5},"fp8":{"w":0.6,"t":2},"q4":{"w":0.34,"t":1.7}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.12,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"stepfun-ai/GOT-OCR-2.0-hf","kind":"HF-transformers"}],"sources":[{"t":"Hugging Face · stepfun-ai/GOT-OCR-2.0-hf","u":"https://huggingface.co/stepfun-ai/GOT-OCR-2.0-hf"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/GOT-OCR-2.0-hf/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/step/#m-got-ocr-2-0-hf"},{"id":"got-ocr2-0","name":"GOT-OCR2_0","hf":"stepfun-ai/GOT-OCR2_0","org":"stepfun-ai","family":"step","series":"GOT-OCR2_0","task":"vlm","pipeline":"image-text-to-text","tags":["ocr"],"released":"2024-09-12","updated":"2025-02-04","gated":false,"params":{"total":0.716,"active":null,"src":"safetensors","q":null,"stTotal":0.716},"moe":false,"ctx":32768,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22},"mem":{"bf16":{"w":1.43,"t":2.9},"fp8":{"w":0.76,"t":2.1},"q4":{"w":0.43,"t":1.8}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.43,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"stepfun-ai/GOT-OCR2_0","kind":"main"}],"sources":[{"t":"Hugging Face · stepfun-ai/GOT-OCR2_0","u":"https://huggingface.co/stepfun-ai/GOT-OCR2_0"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/GOT-OCR2_0/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/step/#m-got-ocr2-0"},{"id":"step-3-5-flash","name":"Step-3.5-Flash","hf":"stepfun-ai/Step-3.5-Flash","org":"stepfun-ai","family":"step","series":"Step-3.5-Flash","task":"llm","pipeline":"text-generation","tags":[],"released":"2026-02-01","updated":"2026-03-17","gated":false,"params":{"total":196,"active":11,"src":"card","q":"# Activated Params 11B · # Total Params (MoE) 196B","stTotal":199.384},"moe":true,"ctx":262144,"arch":{"L":45,"attn":12,"slide":36,"win":512,"kvElems":16384,"kvMethod":"gqa","exotic":[]},"kv":{"8192":3.83,"32768":13.49,"131072":52.14},"mem":{"bf16":{"w":392,"t":435.5},"fp8":{"w":208.25,"t":233.4},"q4":{"w":118.82,"t":135}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":398.77,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"stepfun-ai/Step-3.5-Flash","kind":"main"},{"id":"stepfun-ai/Step-3.5-Flash-FP8","kind":"FP8"},{"id":"stepfun-ai/Step-3.5-Flash-Base","kind":"Base"},{"id":"stepfun-ai/Step-3.5-Flash-GGUF-Q8_0","kind":"GGUF"}],"sources":[{"t":"Hugging Face · stepfun-ai/Step-3.5-Flash","u":"https://huggingface.co/stepfun-ai/Step-3.5-Flash"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/Step-3.5-Flash/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/step-3-5-flash/"},{"id":"step-3-7-flash","name":"Step-3.7-Flash","hf":"stepfun-ai/Step-3.7-Flash","org":"stepfun-ai","family":"step","series":"Step-3.7-Flash","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-05-23","updated":"2026-06-03","gated":false,"params":{"total":198,"active":11,"src":"card","q":"a 198B-parameter sparse Mixture-of-Experts (MoE) vision-language model … it activates approximately 11B parameters per token","stTotal":201.365},"moe":true,"ctx":262144,"arch":{"L":45,"attn":12,"slide":36,"win":512,"kvElems":16384,"kvMethod":"gqa","exotic":[]},"kv":{"8192":3.83,"32768":13.49,"131072":52.14},"mem":{"bf16":{"w":396,"t":439.9},"fp8":{"w":210.38,"t":235.7},"q4":{"w":120.04,"t":136.4}},"fits":{"bf16":{"gpu":"8xh100","mac":null},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":402.73,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"llamacpp","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"stepfun-ai/Step-3.7-Flash-NVFP4","kind":"NVFP4"},{"id":"stepfun-ai/Step-3.7-Flash","kind":"main"},{"id":"stepfun-ai/Step-3.7-Flash-GGUF","kind":"GGUF"},{"id":"stepfun-ai/Step-3.7-Flash-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · stepfun-ai/Step-3.7-Flash","u":"https://huggingface.co/stepfun-ai/Step-3.7-Flash"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/Step-3.7-Flash/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/step-3-7-flash/"},{"id":"step-5-preview","name":"Step-5-Preview","hf":"stepfun-ai/Step-5-Preview","org":"stepfun-ai","family":"step","series":"Step-5-Preview","task":"llm","pipeline":null,"tags":[],"released":"2026-09-20","updated":"2026-10-15","gated":false,"params":{"total":600,"active":27,"src":"card","q":"600B total parameters and 27B active parameters","stTotal":604.34},"moe":true,"ctx":1048576,"arch":{"L":92,"attn":23,"slide":72,"win":512,"kvElems":24576,"kvMethod":"gqa","exotic":[]},"kv":{"8192":11.07,"32768":38.86,"131072":149.99},"mem":{"bf16":{"w":1200,"t":1331.6},"fp8":{"w":637.5,"t":712.8},"q4":{"w":363.75,"t":411.7}},"fits":{"bf16":{"gpu":"8xb300","mac":null},"fp8":{"gpu":"8xh200","mac":null},"q4":{"gpu":"8xh100","mac":null}},"disk":650.31,"native":"F8_E4M3","license":{"id":"other","name":"other","link":"https://huggingface.co/stepfun-ai/Step-5-Preview/blob/main/LICENSE.txt","cls":"custom"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"},{"id":"trtllm","via":"card"}],"variants":[{"id":"stepfun-ai/Step-5-Preview","kind":"main"},{"id":"stepfun-ai/Step-5-Preview-BF16","kind":"BF16"},{"id":"stepfun-ai/Step-5-Preview-NVFP4","kind":"NVFP4"}],"sources":[{"t":"Hugging Face · stepfun-ai/Step-5-Preview","u":"https://huggingface.co/stepfun-ai/Step-5-Preview"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/Step-5-Preview/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/stepfun-ai/Step-5-Preview/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/step-5-preview/"},{"id":"step-audio-chat","name":"Step-Audio-Chat","hf":"stepfun-ai/Step-Audio-Chat","org":"stepfun-ai","family":"step","series":"Step-Audio","task":"omni","pipeline":"audio-text-to-text","tags":[],"released":"2025-02-13","updated":"2025-02-17","gated":false,"params":{"total":131.947,"active":null,"src":"safetensors","q":null,"stTotal":131.947},"moe":false,"ctx":null,"arch":{"L":88,"attn":88,"slide":0,"win":null,"kvElems":24576,"kvMethod":"gqa","exotic":[]},"kv":{"8192":35.43,"32768":141.73,"131072":566.94},"mem":{"bf16":{"w":263.89,"t":326.2},"fp8":{"w":140.19,"t":190.1},"q4":{"w":79.99,"t":123.9}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"h200","mac":"mac256"}},"disk":263.89,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"stepfun-ai/Step-Audio-Chat","kind":"Instruct"}],"sources":[{"t":"Hugging Face · stepfun-ai/Step-Audio-Chat","u":"https://huggingface.co/stepfun-ai/Step-Audio-Chat"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/Step-Audio-Chat/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/step-audio-chat/"},{"id":"step-audio-2-mini","name":"Step-Audio-2-mini","hf":"stepfun-ai/Step-Audio-2-mini","org":"stepfun-ai","family":"step","series":"Step-Audio-2-mini","task":"omni","pipeline":"any-to-any","tags":[],"released":"2025-08-28","updated":"2026-02-14","gated":false,"params":{"total":8.315,"active":null,"src":"safetensors","q":null,"stTotal":8.315},"moe":false,"ctx":16384,"arch":{"L":28,"attn":28,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.47},"mem":{"bf16":{"w":16.63,"t":19.3},"fp8":{"w":8.83,"t":10.7},"q4":{"w":5.04,"t":6.5}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu12","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":16.63,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"}],"variants":[{"id":"stepfun-ai/Step-Audio-2-mini","kind":"main"}],"sources":[{"t":"Hugging Face · stepfun-ai/Step-Audio-2-mini","u":"https://huggingface.co/stepfun-ai/Step-Audio-2-mini"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/Step-Audio-2-mini/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/step/#m-step-audio-2-mini"},{"id":"step-audio-aqaa","name":"Step-Audio-AQAA","hf":"stepfun-ai/Step-Audio-AQAA","org":"stepfun-ai","family":"step","series":"Step-Audio-AQAA","task":"omni","pipeline":null,"tags":[],"released":"2025-06-11","updated":"2025-06-12","gated":false,"params":{"total":136.664,"active":null,"src":"safetensors","q":null,"stTotal":136.664},"moe":false,"ctx":null,"arch":{"L":88,"attn":88,"slide":0,"win":null,"kvElems":24576,"kvMethod":"gqa","exotic":[]},"kv":{"8192":35.43,"32768":141.73,"131072":566.94},"mem":{"bf16":{"w":273.33,"t":336.6},"fp8":{"w":145.21,"t":195.7},"q4":{"w":82.85,"t":127.1}},"fits":{"bf16":{"gpu":"4xpro6000","mac":"mac512"},"fp8":{"gpu":"4xpro6000","mac":"mac512"},"q4":{"gpu":"4xpro6000","mac":"mac256"}},"disk":273.33,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[],"variants":[{"id":"stepfun-ai/Step-Audio-AQAA","kind":"main"}],"sources":[{"t":"Hugging Face · stepfun-ai/Step-Audio-AQAA","u":"https://huggingface.co/stepfun-ai/Step-Audio-AQAA"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/Step-Audio-AQAA/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/step-audio-aqaa/"},{"id":"step-audio-editx","name":"Step-Audio-EditX","hf":"stepfun-ai/Step-Audio-EditX","org":"stepfun-ai","family":"step","series":"Step-Audio-EditX","task":"omni","pipeline":null,"tags":[],"released":"2025-10-29","updated":"2026-02-14","gated":false,"params":{"total":3.53,"active":null,"src":"safetensors","q":null,"stTotal":3.53},"moe":false,"ctx":null,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":6144,"kvMethod":"gqa","exotic":[]},"kv":{"8192":3.22,"32768":12.88,"131072":51.54},"mem":{"bf16":{"w":7.06,"t":11.5},"fp8":{"w":3.75,"t":7.8},"q4":{"w":2.14,"t":6.1}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.06,"native":"BF16","license":{"id":null,"name":null,"link":null,"cls":"unknown"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"stepfun-ai/Step-Audio-EditX","kind":"main"},{"id":"stepfun-ai/Step-Audio-EditX-AWQ-4bit","kind":"AWQ"}],"sources":[{"t":"Hugging Face · stepfun-ai/Step-Audio-EditX","u":"https://huggingface.co/stepfun-ai/Step-Audio-EditX"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/Step-Audio-EditX/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/step/#m-step-audio-editx"},{"id":"step-audio-r1-1","name":"Step-Audio-R1.1","hf":"stepfun-ai/Step-Audio-R1.1","org":"stepfun-ai","family":"step","series":"Step-Audio-R1.1","task":"omni","pipeline":"audio-text-to-text","tags":["reasoning"],"released":"2026-01-14","updated":"2026-02-14","gated":false,"params":{"total":33.487,"active":null,"src":"safetensors","q":null,"stTotal":33.487},"moe":false,"ctx":65536,"arch":{"L":64,"attn":64,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.15,"32768":8.59},"mem":{"bf16":{"w":66.97,"t":76.3},"fp8":{"w":35.58,"t":41.8},"q4":{"w":20.3,"t":25}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":66.97,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"stepfun-ai/Step-Audio-R1.1","kind":"main"}],"sources":[{"t":"Hugging Face · stepfun-ai/Step-Audio-R1.1","u":"https://huggingface.co/stepfun-ai/Step-Audio-R1.1"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/Step-Audio-R1.1/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/step/#m-step-audio-r1-1"},{"id":"step3-vl-10b","name":"Step3-VL-10B","hf":"stepfun-ai/Step3-VL-10B","org":"stepfun-ai","family":"step","series":"Step3-VL","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2026-01-13","updated":"2026-02-04","gated":false,"params":{"total":10.172,"active":null,"src":"safetensors","q":null,"stTotal":10.172},"moe":false,"ctx":65536,"arch":{"L":36,"attn":36,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.21,"32768":4.83},"mem":{"bf16":{"w":20.34,"t":24.1},"fp8":{"w":10.81,"t":13.6},"q4":{"w":6.17,"t":8.5}},"fits":{"bf16":{"gpu":"rtx5090","mac":"mac64"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu12","mac":"mac16"}},"disk":20.34,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"stepfun-ai/Step3-VL-10B","kind":"main"},{"id":"stepfun-ai/Step3-VL-10B-FP8","kind":"FP8"}],"sources":[{"t":"Hugging Face · stepfun-ai/Step3-VL-10B","u":"https://huggingface.co/stepfun-ai/Step3-VL-10B"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/Step3-VL-10B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/step/#m-step3-vl-10b"},{"id":"step3","name":"step3","hf":"stepfun-ai/step3","org":"stepfun-ai","family":"step","series":"step3","task":"vlm","pipeline":"image-text-to-text","tags":[],"released":"2025-07-28","updated":"2026-01-29","gated":false,"params":{"total":321,"active":38,"src":"card","q":"321B total parameters and 38B active","stTotal":320.97},"moe":true,"ctx":null,"arch":{"L":61,"attn":61,"slide":0,"win":null,"kvElems":32768,"kvMethod":"gqa","exotic":[]},"kv":{"8192":32.75,"32768":131,"131072":523.99},"mem":{"bf16":{"w":642,"t":739.5},"fp8":{"w":341.06,"t":408.4},"q4":{"w":194.61,"t":247.3}},"fits":{"bf16":{"gpu":"8xh200","mac":null},"fp8":{"gpu":"8xh100","mac":null},"q4":{"gpu":"4xpro6000","mac":"mac512"}},"disk":641.94,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/stepfun-ai/step3/blob/main/LICENSE","cls":"open"},"runtimes":[{"id":"vllm","via":"card"},{"id":"sglang","via":"card"},{"id":"transformers","via":"card"}],"variants":[{"id":"stepfun-ai/step3","kind":"main"},{"id":"stepfun-ai/step3-fp8","kind":"FP8"}],"sources":[{"t":"Hugging Face · stepfun-ai/step3","u":"https://huggingface.co/stepfun-ai/step3"},{"t":"config.json","u":"https://huggingface.co/stepfun-ai/step3/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/stepfun-ai/step3/blob/main/LICENSE"}],"page":"https://aimap.page/en/models/compute/open-models/step3/"},{"id":"wan-dancer-14b","name":"Wan-Dancer-14B","hf":"Wan-AI/Wan-Dancer-14B","org":"Wan-AI","family":"wan","series":"Wan-Dancer","task":"video","pipeline":"image-to-video","tags":[],"released":"2026-07-10","updated":"2026-07-17","gated":false,"params":{"total":14,"active":null,"src":"name","q":null,"stTotal":null},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":28,"t":31.3},"fp8":{"w":14.88,"t":16.9},"q4":{"w":8.49,"t":9.8}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac24"}},"disk":68.98,"native":null,"license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan-Dancer-14B","kind":"main"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan-Dancer-14B","u":"https://huggingface.co/Wan-AI/Wan-Dancer-14B"},{"t":"config.json","u":"https://huggingface.co/Wan-AI/Wan-Dancer-14B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan-dancer-14b"},{"id":"wan2-1-flf2v-14b-720p","name":"Wan2.1-FLF2V-14B-720P","hf":"Wan-AI/Wan2.1-FLF2V-14B-720P","org":"Wan-AI","family":"wan","series":"Wan2.1-FLF2V-720P","task":"video","pipeline":null,"tags":[],"released":"2025-04-17","updated":"2025-04-17","gated":false,"params":{"total":16.396,"active":null,"src":"safetensors","q":null,"stTotal":16.396},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":32.79,"t":36.6},"fp8":{"w":17.42,"t":19.7},"q4":{"w":9.94,"t":11.4}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":65.58,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.1-FLF2V-14B-720P","kind":"main"},{"id":"Wan-AI/Wan2.1-FLF2V-14B-720P-diffusers","kind":"Diffusers"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.1-FLF2V-14B-720P","u":"https://huggingface.co/Wan-AI/Wan2.1-FLF2V-14B-720P"},{"t":"config.json","u":"https://huggingface.co/Wan-AI/Wan2.1-FLF2V-14B-720P/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-1-flf2v-14b-720p"},{"id":"wan2-1-i2v-14b-480p","name":"Wan2.1-I2V-14B-480P","hf":"Wan-AI/Wan2.1-I2V-14B-480P","org":"Wan-AI","family":"wan","series":"Wan2.1-I2V-480P","task":"video","pipeline":"image-to-video","tags":[],"released":"2025-02-25","updated":"2025-02-26","gated":false,"params":{"total":16.395,"active":null,"src":"safetensors","q":null,"stTotal":16.395},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":32.79,"t":36.6},"fp8":{"w":17.42,"t":19.7},"q4":{"w":9.94,"t":11.4}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":65.58,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P/blob/main/LICENSE.txt","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.1-I2V-14B-480P","kind":"main"},{"id":"Wan-AI/Wan2.1-I2V-14B-480P-Diffusers","kind":"Diffusers"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.1-I2V-14B-480P","u":"https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P"},{"t":"config.json","u":"https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-1-i2v-14b-480p"},{"id":"wan2-1-i2v-14b-720p-diffusers","name":"Wan2.1-I2V-14B-720P-Diffusers","hf":"Wan-AI/Wan2.1-I2V-14B-720P-Diffusers","org":"Wan-AI","family":"wan","series":"Wan2.1-I2V-720P","task":"video","pipeline":"image-to-video","tags":[],"released":"2025-03-01","updated":"2025-04-04","gated":false,"params":{"total":16.395,"active":null,"src":"safetensors","q":null,"stTotal":16.395},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":32.79,"t":36.6},"fp8":{"w":17.42,"t":19.7},"q4":{"w":9.94,"t":11.4}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":90.08,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.1-I2V-14B-720P-Diffusers","kind":"Diffusers"},{"id":"Wan-AI/Wan2.1-I2V-14B-720P","kind":"main"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.1-I2V-14B-720P-Diffusers","u":"https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P-Diffusers"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-1-i2v-14b-720p-diffusers"},{"id":"wan2-1-t2v-1-3b-diffusers","name":"Wan2.1-T2V-1.3B-Diffusers","hf":"Wan-AI/Wan2.1-T2V-1.3B-Diffusers","org":"Wan-AI","family":"wan","series":"Wan2.1-T2V","task":"video","pipeline":"text-to-video","tags":[],"released":"2025-03-01","updated":"2025-04-04","gated":false,"params":{"total":1.419,"active":null,"src":"safetensors","q":null,"stTotal":1.419},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":2.84,"t":3.6},"fp8":{"w":1.51,"t":2.2},"q4":{"w":0.86,"t":1.4}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":28.91,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.1-T2V-1.3B-Diffusers","kind":"Diffusers"},{"id":"Wan-AI/Wan2.1-T2V-1.3B","kind":"main"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.1-T2V-1.3B-Diffusers","u":"https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B-Diffusers"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-1-t2v-1-3b-diffusers"},{"id":"wan2-1-t2v-14b-diffusers","name":"Wan2.1-T2V-14B-Diffusers","hf":"Wan-AI/Wan2.1-T2V-14B-Diffusers","org":"Wan-AI","family":"wan","series":"Wan2.1-T2V","task":"video","pipeline":"text-to-video","tags":[],"released":"2025-03-01","updated":"2025-04-04","gated":false,"params":{"total":14.288,"active":null,"src":"safetensors","q":null,"stTotal":14.288},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":28.58,"t":31.9},"fp8":{"w":15.18,"t":17.2},"q4":{"w":8.66,"t":10}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac24"}},"disk":80.39,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.1-T2V-14B-Diffusers","kind":"Diffusers"},{"id":"Wan-AI/Wan2.1-T2V-14B","kind":"main"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.1-T2V-14B-Diffusers","u":"https://huggingface.co/Wan-AI/Wan2.1-T2V-14B-Diffusers"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-1-t2v-14b-diffusers"},{"id":"wan2-1-vace-1-3b","name":"Wan2.1-VACE-1.3B","hf":"Wan-AI/Wan2.1-VACE-1.3B","org":"Wan-AI","family":"wan","series":"Wan2.1-VACE","task":"video","pipeline":"image-to-video","tags":[],"released":"2025-05-13","updated":"2025-05-19","gated":false,"params":{"total":2.154,"active":null,"src":"safetensors","q":null,"stTotal":2.154},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":4.31,"t":5.2},"fp8":{"w":2.29,"t":3},"q4":{"w":1.31,"t":1.9}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":7.15,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B/blob/main/LICENSE.txt","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.1-VACE-1.3B","kind":"main"},{"id":"Wan-AI/Wan2.1-VACE-1.3B-diffusers","kind":"Diffusers"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.1-VACE-1.3B","u":"https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B"},{"t":"config.json","u":"https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-1-vace-1-3b"},{"id":"wan2-1-vace-14b","name":"Wan2.1-VACE-14B","hf":"Wan-AI/Wan2.1-VACE-14B","org":"Wan-AI","family":"wan","series":"Wan2.1-VACE","task":"video","pipeline":"image-to-video","tags":[],"released":"2025-05-13","updated":"2025-05-19","gated":false,"params":{"total":17.338,"active":null,"src":"safetensors","q":null,"stTotal":17.338},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":34.68,"t":38.6},"fp8":{"w":18.42,"t":20.8},"q4":{"w":10.51,"t":12.1}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":63.25,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":"https://huggingface.co/Wan-AI/Wan2.1-VACE-14B/blob/main/LICENSE.txt","cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.1-VACE-14B","kind":"main"},{"id":"Wan-AI/Wan2.1-VACE-14B-diffusers","kind":"Diffusers"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.1-VACE-14B","u":"https://huggingface.co/Wan-AI/Wan2.1-VACE-14B"},{"t":"config.json","u":"https://huggingface.co/Wan-AI/Wan2.1-VACE-14B/blob/main/config.json"},{"t":"License","u":"https://huggingface.co/Wan-AI/Wan2.1-VACE-14B/blob/main/LICENSE.txt"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-1-vace-14b"},{"id":"wan2-2-animate-14b-diffusers","name":"Wan2.2-Animate-14B-Diffusers","hf":"Wan-AI/Wan2.2-Animate-14B-Diffusers","org":"Wan-AI","family":"wan","series":"Wan2.2-Animate","task":"video","pipeline":null,"tags":[],"released":"2025-11-12","updated":"2025-11-13","gated":false,"params":{"total":17.275,"active":null,"src":"safetensors","q":null,"stTotal":17.275},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":34.55,"t":38.5},"fp8":{"w":18.35,"t":20.7},"q4":{"w":10.47,"t":12}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":82.23,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.2-Animate-14B-Diffusers","kind":"Diffusers"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.2-Animate-14B-Diffusers","u":"https://huggingface.co/Wan-AI/Wan2.2-Animate-14B-Diffusers"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-2-animate-14b-diffusers"},{"id":"wan2-2-animate-2-14b-diffusers","name":"Wan2.2-Animate-2-14B-Diffusers","hf":"Wan-AI/Wan2.2-Animate-2-14B-Diffusers","org":"Wan-AI","family":"wan","series":"Wan2.2-Animate-2","task":"video","pipeline":null,"tags":[],"released":"2026-08-06","updated":"2026-08-13","gated":false,"params":{"total":16.395,"active":null,"src":"safetensors","q":null,"stTotal":16.395},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":32.79,"t":36.6},"fp8":{"w":17.42,"t":19.7},"q4":{"w":9.94,"t":11.4}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":45.92,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.2-Animate-2-14B-Diffusers","kind":"Diffusers"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.2-Animate-2-14B-Diffusers","u":"https://huggingface.co/Wan-AI/Wan2.2-Animate-2-14B-Diffusers"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-2-animate-2-14b-diffusers"},{"id":"wan2-2-animate-2-14b-distilled-diffusers","name":"Wan2.2-Animate-2-14B-Distilled-Diffusers","hf":"Wan-AI/Wan2.2-Animate-2-14B-Distilled-Diffusers","org":"Wan-AI","family":"wan","series":"Wan2.2-Animate-2-Distilled","task":"video","pipeline":null,"tags":[],"released":"2026-08-06","updated":"2026-08-13","gated":false,"params":{"total":16.395,"active":null,"src":"safetensors","q":null,"stTotal":16.395},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":32.79,"t":36.6},"fp8":{"w":17.42,"t":19.7},"q4":{"w":9.94,"t":11.4}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":45.92,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.2-Animate-2-14B-Distilled-Diffusers","kind":"Diffusers"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.2-Animate-2-14B-Distilled-Diffusers","u":"https://huggingface.co/Wan-AI/Wan2.2-Animate-2-14B-Distilled-Diffusers"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-2-animate-2-14b-distilled-diffusers"},{"id":"wan2-2-i2v-a14b-diffusers","name":"Wan2.2-I2V-A14B-Diffusers","hf":"Wan-AI/Wan2.2-I2V-A14B-Diffusers","org":"Wan-AI","family":"wan","series":"Wan2.2-I2V","task":"video","pipeline":"image-to-video","tags":[],"released":"2025-07-28","updated":"2025-08-09","gated":false,"params":{"total":14.289,"active":14,"src":"safetensors","q":null,"stTotal":14.289},"moe":true,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":28.58,"t":31.9},"fp8":{"w":15.18,"t":17.2},"q4":{"w":8.66,"t":10}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac24"}},"disk":126.18,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.2-Animate-14B","kind":"main"},{"id":"Wan-AI/Wan2.2-I2V-A14B-Diffusers","kind":"Diffusers"},{"id":"Wan-AI/Wan2.2-I2V-A14B","kind":"main"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.2-I2V-A14B-Diffusers","u":"https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-2-i2v-a14b-diffusers"},{"id":"wan2-2-s2v-14b","name":"Wan2.2-S2V-14B","hf":"Wan-AI/Wan2.2-S2V-14B","org":"Wan-AI","family":"wan","series":"Wan2.2-S2V","task":"video","pipeline":"image-to-video","tags":[],"released":"2025-08-25","updated":"2025-09-17","gated":false,"params":{"total":16.296,"active":null,"src":"safetensors","q":null,"stTotal":16.296},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":32.59,"t":36.4},"fp8":{"w":17.31,"t":19.5},"q4":{"w":9.88,"t":11.4}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu16","mac":"mac24"}},"disk":32.59,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.2-S2V-14B","kind":"main"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.2-S2V-14B","u":"https://huggingface.co/Wan-AI/Wan2.2-S2V-14B"},{"t":"config.json","u":"https://huggingface.co/Wan-AI/Wan2.2-S2V-14B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-2-s2v-14b"},{"id":"wan2-2-t2v-a14b-diffusers","name":"Wan2.2-T2V-A14B-Diffusers","hf":"Wan-AI/Wan2.2-T2V-A14B-Diffusers","org":"Wan-AI","family":"wan","series":"Wan2.2-T2V","task":"video","pipeline":"text-to-video","tags":[],"released":"2025-07-28","updated":"2025-08-09","gated":false,"params":{"total":14.288,"active":14,"src":"safetensors","q":null,"stTotal":14.288},"moe":true,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":28.58,"t":31.9},"fp8":{"w":15.18,"t":17.2},"q4":{"w":8.66,"t":10}},"fits":{"bf16":{"gpu":"2x5090","mac":"mac64"},"fp8":{"gpu":"rtx4090","mac":"mac36"},"q4":{"gpu":"gpu12","mac":"mac24"}},"disk":126.18,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.2-T2V-A14B-Diffusers","kind":"Diffusers"},{"id":"Wan-AI/Wan2.2-T2V-A14B","kind":"main"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.2-T2V-A14B-Diffusers","u":"https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-2-t2v-a14b-diffusers"},{"id":"wan2-2-ti2v-5b-diffusers","name":"Wan2.2-TI2V-5B-Diffusers","hf":"Wan-AI/Wan2.2-TI2V-5B-Diffusers","org":"Wan-AI","family":"wan","series":"Wan2.2-TI2V","task":"video","pipeline":"text-to-video","tags":[],"released":"2025-07-28","updated":"2025-08-09","gated":false,"params":{"total":5,"active":null,"src":"safetensors","q":null,"stTotal":5},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":10,"t":11.5},"fp8":{"w":5.31,"t":6.3},"q4":{"w":3.03,"t":3.8}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":34.18,"native":"F32","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"diffusers","via":"card"},{"id":"comfyui","via":"card"}],"variants":[{"id":"Wan-AI/Wan2.2-TI2V-5B-Diffusers","kind":"Diffusers"},{"id":"Wan-AI/Wan2.2-TI2V-5B","kind":"main"}],"sources":[{"t":"Hugging Face · Wan-AI/Wan2.2-TI2V-5B-Diffusers","u":"https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers"}],"page":"https://aimap.page/en/models/compute/open-models/family/wan/#m-wan2-2-ti2v-5b-diffusers"},{"id":"whisper-large-v3","name":"whisper-large-v3","hf":"openai/whisper-large-v3","org":"openai","family":"whisper","series":"whisper-large","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2023-11-07","updated":"2024-08-12","gated":false,"params":{"total":1.543,"active":null,"src":"safetensors","q":null,"stTotal":1.543},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":3.09,"t":3.9},"fp8":{"w":1.64,"t":2.3},"q4":{"w":0.94,"t":1.5}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":9.26,"native":"F16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"openai/whisper-large-v3","kind":"main"}],"sources":[{"t":"Hugging Face · openai/whisper-large-v3","u":"https://huggingface.co/openai/whisper-large-v3"},{"t":"config.json","u":"https://huggingface.co/openai/whisper-large-v3/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/whisper/#m-whisper-large-v3"},{"id":"whisper-large-v3-turbo","name":"whisper-large-v3-turbo","hf":"openai/whisper-large-v3-turbo","org":"openai","family":"whisper","series":"whisper-large-turbo","task":"asr","pipeline":"automatic-speech-recognition","tags":[],"released":"2024-10-01","updated":"2024-10-04","gated":false,"params":{"total":0.809,"active":null,"src":"safetensors","q":null,"stTotal":0.809},"moe":false,"ctx":null,"arch":null,"kv":null,"mem":{"bf16":{"w":1.62,"t":2.3},"fp8":{"w":0.86,"t":1.4},"q4":{"w":0.49,"t":1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":1.62,"native":"F16","license":{"id":"mit","name":"MIT","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"}],"variants":[{"id":"openai/whisper-large-v3-turbo","kind":"main"}],"sources":[{"t":"Hugging Face · openai/whisper-large-v3-turbo","u":"https://huggingface.co/openai/whisper-large-v3-turbo"},{"t":"config.json","u":"https://huggingface.co/openai/whisper-large-v3-turbo/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/whisper/#m-whisper-large-v3-turbo"},{"id":"yi-1-5-6b","name":"Yi-1.5-6B","hf":"01-ai/Yi-1.5-6B","org":"01-ai","family":"yi","series":"Yi-1.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-11","updated":"2024-06-26","gated":false,"params":{"total":6.061,"active":null,"src":"safetensors","q":null,"stTotal":6.061},"moe":false,"ctx":4096,"arch":{"L":32,"attn":32,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.54},"mem":{"bf16":{"w":12.12,"t":14.4},"fp8":{"w":6.44,"t":8.1},"q4":{"w":3.67,"t":5.1}},"fits":{"bf16":{"gpu":"gpu16","mac":"mac24"},"fp8":{"gpu":"gpu12","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":12.12,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"hf-library"}],"variants":[{"id":"01-ai/Yi-1.5-6B","kind":"main"},{"id":"01-ai/Yi-1.5-6B-Chat","kind":"Instruct"}],"sources":[{"t":"Hugging Face · 01-ai/Yi-1.5-6B","u":"https://huggingface.co/01-ai/Yi-1.5-6B"},{"t":"config.json","u":"https://huggingface.co/01-ai/Yi-1.5-6B/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/yi/#m-yi-1-5-6b"},{"id":"yi-1-5-9b-chat","name":"Yi-1.5-9B-Chat","hf":"01-ai/Yi-1.5-9B-Chat","org":"01-ai","family":"yi","series":"Yi-1.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-10","updated":"2024-06-26","gated":false,"params":{"total":8.829,"active":null,"src":"safetensors","q":null,"stTotal":8.829},"moe":false,"ctx":4096,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81},"mem":{"bf16":{"w":17.66,"t":20.7},"fp8":{"w":9.38,"t":11.6},"q4":{"w":5.35,"t":7.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.66,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"hf-library"}],"variants":[{"id":"01-ai/Yi-1.5-9B-Chat","kind":"Instruct"},{"id":"01-ai/Yi-1.5-9B","kind":"main"}],"sources":[{"t":"Hugging Face · 01-ai/Yi-1.5-9B-Chat","u":"https://huggingface.co/01-ai/Yi-1.5-9B-Chat"},{"t":"config.json","u":"https://huggingface.co/01-ai/Yi-1.5-9B-Chat/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/yi/#m-yi-1-5-9b-chat"},{"id":"yi-1-5-34b-chat","name":"Yi-1.5-34B-Chat","hf":"01-ai/Yi-1.5-34B-Chat","org":"01-ai","family":"yi","series":"Yi-1.5","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-10","updated":"2024-08-27","gated":false,"params":{"total":34.389,"active":null,"src":"safetensors","q":null,"stTotal":34.389},"moe":false,"ctx":4096,"arch":{"L":60,"attn":60,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.01},"mem":{"bf16":{"w":68.78,"t":78.2},"fp8":{"w":36.54,"t":42.7},"q4":{"w":20.85,"t":25.4}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":68.78,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"hf-library"}],"variants":[{"id":"01-ai/Yi-1.5-34B-Chat","kind":"Instruct"},{"id":"01-ai/Yi-1.5-34B","kind":"main"}],"sources":[{"t":"Hugging Face · 01-ai/Yi-1.5-34B-Chat","u":"https://huggingface.co/01-ai/Yi-1.5-34B-Chat"},{"t":"config.json","u":"https://huggingface.co/01-ai/Yi-1.5-34B-Chat/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/yi/#m-yi-1-5-34b-chat"},{"id":"yi-1-5-9b-chat-16k","name":"Yi-1.5-9B-Chat-16K","hf":"01-ai/Yi-1.5-9B-Chat-16K","org":"01-ai","family":"yi","series":"Yi-1.5-16K","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-15","updated":"2024-06-26","gated":false,"params":{"total":8.829,"active":null,"src":"safetensors","q":null,"stTotal":8.829},"moe":false,"ctx":16384,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81},"mem":{"bf16":{"w":17.66,"t":20.7},"fp8":{"w":9.38,"t":11.6},"q4":{"w":5.35,"t":7.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.66,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"hf-library"}],"variants":[{"id":"01-ai/Yi-1.5-9B-Chat-16K","kind":"Instruct"}],"sources":[{"t":"Hugging Face · 01-ai/Yi-1.5-9B-Chat-16K","u":"https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K"},{"t":"config.json","u":"https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/yi/#m-yi-1-5-9b-chat-16k"},{"id":"yi-1-5-34b-chat-16k","name":"Yi-1.5-34B-Chat-16K","hf":"01-ai/Yi-1.5-34B-Chat-16K","org":"01-ai","family":"yi","series":"Yi-1.5-16K","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-15","updated":"2024-06-26","gated":false,"params":{"total":34.389,"active":null,"src":"safetensors","q":null,"stTotal":34.389},"moe":false,"ctx":16384,"arch":{"L":60,"attn":60,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.01},"mem":{"bf16":{"w":68.78,"t":78.2},"fp8":{"w":36.54,"t":42.7},"q4":{"w":20.85,"t":25.4}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":68.78,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"hf-library"}],"variants":[{"id":"01-ai/Yi-1.5-34B-Chat-16K","kind":"Instruct"}],"sources":[{"t":"Hugging Face · 01-ai/Yi-1.5-34B-Chat-16K","u":"https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K"},{"t":"config.json","u":"https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/yi/#m-yi-1-5-34b-chat-16k"},{"id":"yi-1-5-9b-32k","name":"Yi-1.5-9B-32K","hf":"01-ai/Yi-1.5-9B-32K","org":"01-ai","family":"yi","series":"Yi-1.5-32K","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-15","updated":"2024-06-26","gated":false,"params":{"total":8.829,"active":null,"src":"safetensors","q":null,"stTotal":8.829},"moe":false,"ctx":32768,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22},"mem":{"bf16":{"w":17.66,"t":20.7},"fp8":{"w":9.38,"t":11.6},"q4":{"w":5.35,"t":7.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.66,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"hf-library"}],"variants":[{"id":"01-ai/Yi-1.5-9B-32K","kind":"main"}],"sources":[{"t":"Hugging Face · 01-ai/Yi-1.5-9B-32K","u":"https://huggingface.co/01-ai/Yi-1.5-9B-32K"},{"t":"config.json","u":"https://huggingface.co/01-ai/Yi-1.5-9B-32K/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/yi/#m-yi-1-5-9b-32k"},{"id":"yi-1-5-34b-32k","name":"Yi-1.5-34B-32K","hf":"01-ai/Yi-1.5-34B-32K","org":"01-ai","family":"yi","series":"Yi-1.5-32K","task":"llm","pipeline":"text-generation","tags":[],"released":"2024-05-15","updated":"2024-06-26","gated":false,"params":{"total":34.389,"active":null,"src":"safetensors","q":null,"stTotal":34.389},"moe":false,"ctx":32768,"arch":{"L":60,"attn":60,"slide":0,"win":null,"kvElems":2048,"kvMethod":"gqa","exotic":[]},"kv":{"8192":2.01,"32768":8.05},"mem":{"bf16":{"w":68.78,"t":78.2},"fp8":{"w":36.54,"t":42.7},"q4":{"w":20.85,"t":25.4}},"fits":{"bf16":{"gpu":"pro6000","mac":"mac128"},"fp8":{"gpu":"2x5090","mac":"mac64"},"q4":{"gpu":"rtx5090","mac":"mac64"}},"disk":68.78,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"hf-library"}],"variants":[{"id":"01-ai/Yi-1.5-34B-32K","kind":"main"}],"sources":[{"t":"Hugging Face · 01-ai/Yi-1.5-34B-32K","u":"https://huggingface.co/01-ai/Yi-1.5-34B-32K"},{"t":"config.json","u":"https://huggingface.co/01-ai/Yi-1.5-34B-32K/blob/main/config.json"}],"page":"https://aimap.page/en/models/compute/open-models/family/yi/#m-yi-1-5-34b-32k"},{"id":"yi-coder-1-5b-chat","name":"Yi-Coder-1.5B-Chat","hf":"01-ai/Yi-Coder-1.5B-Chat","org":"01-ai","family":"yi","series":"Yi-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-08-21","updated":"2024-09-06","gated":false,"params":{"total":1.476,"active":null,"src":"safetensors","q":null,"stTotal":1.476},"moe":false,"ctx":131072,"arch":{"L":24,"attn":24,"slide":0,"win":null,"kvElems":4096,"kvMethod":"gqa","exotic":[]},"kv":{"8192":1.61,"32768":6.44,"131072":25.77},"mem":{"bf16":{"w":2.95,"t":5.4},"fp8":{"w":1.57,"t":3.8},"q4":{"w":0.89,"t":3.1}},"fits":{"bf16":{"gpu":"gpu8","mac":"mac16"},"fp8":{"gpu":"gpu8","mac":"mac16"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":2.95,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"yi-coder:1.5b","url":"https://ollama.com/library/yi-coder"}],"variants":[{"id":"01-ai/Yi-Coder-1.5B-Chat","kind":"Instruct"}],"sources":[{"t":"Hugging Face · 01-ai/Yi-Coder-1.5B-Chat","u":"https://huggingface.co/01-ai/Yi-Coder-1.5B-Chat"},{"t":"config.json","u":"https://huggingface.co/01-ai/Yi-Coder-1.5B-Chat/blob/main/config.json"},{"t":"Ollama library · yi-coder","u":"https://ollama.com/library/yi-coder"}],"page":"https://aimap.page/en/models/compute/open-models/family/yi/#m-yi-coder-1-5b-chat"},{"id":"yi-coder-9b-chat","name":"Yi-Coder-9B-Chat","hf":"01-ai/Yi-Coder-9B-Chat","org":"01-ai","family":"yi","series":"Yi-Coder","task":"llm","pipeline":"text-generation","tags":["coding"],"released":"2024-08-21","updated":"2024-09-12","gated":false,"params":{"total":8.829,"active":null,"src":"safetensors","q":null,"stTotal":8.829},"moe":false,"ctx":131072,"arch":{"L":48,"attn":48,"slide":0,"win":null,"kvElems":1024,"kvMethod":"gqa","exotic":[]},"kv":{"8192":0.81,"32768":3.22,"131072":12.88},"mem":{"bf16":{"w":17.66,"t":20.7},"fp8":{"w":9.38,"t":11.6},"q4":{"w":5.35,"t":7.2}},"fits":{"bf16":{"gpu":"rtx4090","mac":"mac36"},"fp8":{"gpu":"gpu16","mac":"mac24"},"q4":{"gpu":"gpu8","mac":"mac16"}},"disk":17.66,"native":"BF16","license":{"id":"apache-2.0","name":"Apache-2.0","link":null,"cls":"open"},"runtimes":[{"id":"transformers","via":"card"},{"id":"ollama","via":"ollama-library","tag":"yi-coder:9b","url":"https://ollama.com/library/yi-coder"}],"variants":[{"id":"01-ai/Yi-Coder-9B-Chat","kind":"Instruct"},{"id":"01-ai/Yi-Coder-9B","kind":"main"}],"sources":[{"t":"Hugging Face · 01-ai/Yi-Coder-9B-Chat","u":"https://huggingface.co/01-ai/Yi-Coder-9B-Chat"},{"t":"config.json","u":"https://huggingface.co/01-ai/Yi-Coder-9B-Chat/blob/main/config.json"},{"t":"Ollama library · yi-coder","u":"https://ollama.com/library/yi-coder"}],"page":"https://aimap.page/en/models/compute/open-models/family/yi/#m-yi-coder-9b-chat"}]}