MXFP4 Open on Hugging Face
Parameters
117B
Weights (est.)
≈ 65.8 GB
Mac memory (est.)
96 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/gpt-oss-120b-MXFP4-Q4 --prompt "Hello"
Details
- Base model
- openai/gpt-oss-120b (quantized) · gpt oss 120b on the radar →
- Vendor
- OpenAI · gpt-oss
- Task
- Text generation
- Quantisation
- MXFP4
- Licence
- apache-2.0
- Downloads
- 1.3K in the last 30 days · 21K all time · 7 likes
- Published
- 2025-08-29 · updated 2025-08-29 (1y ago)
- Tags
- gpt_oss, vllm
Other MLX builds of openai/gpt-oss-120b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gpt-oss-120b-MXFP4-Q8 | MXFP4 | ≈ 65.8 GB | 96 GB+ | 4.3K |
| gpt-oss-120b-MXFP4-Q4 (this one) | MXFP4 | ≈ 65.8 GB | 96 GB+ | 1.3K |
| gpt-oss-120b-mxfp4-bf16 | MXFP4 | ≈ 68.8 GB | 96 GB+ | 685 |