Open-weight LLMs you can run yourself › gpt-oss-120b
Updated · public data
OpenAI · Open weights
gpt-oss-120b is an open-weight LLM from OpenAI with 117B parameters. It needs about 71 GB of memory at 4-bit — smallest setups that run it: Mac 128 GB.
| Parameters | 117B |
| Memory to run | ~71 GB (at 4-bit, rough estimate) |
| Downloads | 3.4M (last 30 days on Hugging Face) |
| Likes | 5.4K |
| License | Apache 2.0 |
| First uploaded | Aug 4, 2025 |
| Hosted from | $0.03 (per 1M input tokens · cheapest on OpenRouter) |
| Phone | iPhone · Android: too big |
| PC with a GPU | 8 GB: too big · 12 GB: too big · 16 GB: too big · 24 GB: too big · 32 GB: too big |
| PC or laptop, no GPU | 16 GB: too big · 32 GB: too big · 64 GB: too big |
| Mac | 16 GB: too big · 32 GB: too big · 64 GB: too big · 128 GB: fits |
huggingface.co/openai/gpt-oss-120b
Data: Hugging Face (official accounts), Oct 16, 2026 · memory is a rough estimate (4-bit for LLMs, 8-bit for image and video, plus 10%) · hosted price: OpenRouter