// Open-model VRAM table · family
Thinking Machines Inkling: local deployment & VRAM
2 open-weight models from Thinking Machines Lab (4 official repos incl. quantised builds). At 4-bit they range from 185 GB (Inkling-Small) to 651 GB (Inkling).
official orgs: thinkingmachineslatest 2026-07-27memory = estimate
01Vision-language (2)
| Model | Params | Context | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|---|
| Inkling-Small | 276B / 12B | — | 608 GB | 185 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB | Commercial OK | 2026-07-27 |
| Inkling | 975B / 41B | — | 2.15 TB | 651 GB | 8 × H200 (1,128GB) | — | Commercial OK | 2026-07-14 |
02Other families
Qwen · IBM Granite · NVIDIA Nemotron · Gemma · Mistral / Magistral / Devstral · GLM / CogVideoX (Z.ai) · DeepSeek · Ai2 OLMo / Molmo · Ant Ling / Ring / Ming · Liquid LFM · MiniCPM / VoxCPM · Tencent Hunyuan / Hy · Phi · Llama · Meituan LongCat · Jina embeddings & rerankers · Wan · Kimi · Cohere Command / Aya · Xiaomi MiMo · FLUX · Microsoft VibeVoice / Fara / Harrier · InternLM / Intern-S · StepFun Step · MiniMax · Baidu ERNIE · NVIDIA Parakeet / Canary speech · Stable Diffusion / Stable Audio · Yi (01.AI) · ByteDance Seed · SmolLM / SmolVLM · BGE embeddings & rerankers · LTX Video · FunAudioLLM speech · gpt-oss · poolside Laguna · Whisper · Baichuan · xAI Grok · rednote dots
Totals include 10% + 0.5GB overhead and one 8K-token KV cache for text models. Estimates only. Method →