OpenAI · open-weights model
gpt-oss-120b
gpt-oss-120b is a 117B-parameter model (MoE, 5.1B active) by OpenAI. Its smallest quant (MXFP4) needs at least 64.4GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 6 of the 50 machines we track.
- Parameters
- 117B total · 5.1B active
- Layers
- 36
- Max context
- 128K
- Attention
- HYBRID
- License
- apache-2.0
Config from openai/gpt-oss-120b
Quants and what they need
Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.
| Quant | File size | Needs ≥ |
|---|---|---|
| MXFP4 | 63.4 GB | 64.4 GB |
What runs gpt-oss-120b
Every machine we track, graded at its best clean-fit quant.
Verdicts computed from published specs and measured GGUF sizes — how the math works.