// Open-model VRAM table · family
gpt-oss: local deployment & VRAM
4 open-weight models from OpenAI (4 official repos incl. quantised builds). At 4-bit they range from 14.7 GB (gpt-oss-20b) to 78.8 GB (gpt-oss-120b).
official orgs: openailatest 2025-09-18memory = estimate
01Text LLM (2)
| Model | Params | Context | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|---|
| gpt-oss-20b | 21B / 3.6B | 128K | 46.9 GB | 14.7 GB | RTX 4090 24GB | Mac 36GB | Commercial OK | 2025-08-04 |
| gpt-oss-120b | 117B / 5.1B | 128K | 258 GB | 78.8 GB | RTX PRO 6000 96GB | Mac 128GB | Commercial OK | 2025-08-04 |
02Safety / guard (2)
| Model | Params | Context | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|---|
| gpt-oss-safeguard-20b | 21B / 3.6B | 128K | 46.9 GB | 14.7 GB | RTX 4090 24GB | Mac 36GB | Commercial OK | 2025-09-18 |
| gpt-oss-safeguard-120b | 117B / 5.1B | 128K | 258 GB | 78.8 GB | RTX PRO 6000 96GB | Mac 128GB | Commercial OK | 2025-09-18 |
03Other 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 · poolside Laguna · Whisper · Baichuan · Thinking Machines Inkling · xAI Grok · rednote dots
Totals include 10% + 0.5GB overhead and one 8K-token KV cache for text models. Estimates only. Method →