GPT-OSS 120B
OpenAI · 116.8B (5.1B active, MoE) · up to 128K context · apache-2.0
This is the model that made a 64GB M-series Mac a genuinely useful frontier-model machine, since only 5.1B parameters activate per token despite the 117B total. On a 128GB Mac Studio it runs quickly enough for interactive use, which is unusual for a model this large.
On a M4 Pro with 48 GB
macOS9.6 GBweights65.7 GBKV cache0.6 GBover27.9 GB
- Weights
- 65.7 GB
- KV cache
- 0.6 GB
- Usable RAM
- 38.4 GB
- Headroom
- 0.0 GB
- Generation
- 74.2 tok/sest.
- Prompt processing
- 177 tok/sest.
- First token (1K prompt)
- 5.8 sest.
Decode speed is bandwidth ÷ active weight bytes, at 273 GB/s and 78% efficiency. These are modelled figures, not measurements.
Every quantization, on your Mac
| Quant | Weights | + KV | Verdict | Speed est. | Repo |
|---|---|---|---|---|---|
| q4 | 65.7 GB | 66.3 GB | OVER BY 27.9 GB | 74.2 tok/s | gpt-oss-120b-MXFP4-Q4 |
| q8 | 124.1 GB | 124.7 GB | OVER BY 86.3 GB | 39.3 tok/s | gpt-oss-120b-MXFP4-Q8 |
We never host weights. Every link goes to Hugging Face.
Run it
Chat
mlx_lm.chat --model mlx-community/gpt-oss-120b-MXFP4-Q4Serve an OpenAI-compatible endpoint
mlx_lm.server --model mlx-community/gpt-oss-120b-MXFP4-Q4 --port 8080How far can you push the context
2K tokensOVER BY 27.5 GB
cache 0.2 GB
8K tokensOVER BY 27.9 GB
cache 0.6 GB
32K tokensOVER BY 29.7 GB
cache 2.4 GB
128K tokensOVER BY 37.0 GB
cache 9.7 GB
Which Macs run this
| Chip | Smallest RAM that fits | Speed est. |
|---|---|---|
| M1 | no configuration | — |
| M1 Pro | no configuration | — |
| M1 Max | no configuration | — |
| M1 Ultra | 128 GB | 226 tok/s |
| M2 | no configuration | — |
| M2 Pro | no configuration | — |
| M2 Max | 96 GB | 112 tok/s |
| M2 Ultra | 128 GB | 229 tok/s |
| M3 | no configuration | — |
| M3 Pro | no configuration | — |
| M3 Max (14-core CPU) | no configuration | — |
| M3 Max (16-core CPU) | 96 GB | 112 tok/s |
| M3 Ultra | 96 GB | 237 tok/s |
| M4 | no configuration | — |
| M4 Pro | no configuration | — |
| M4 Max (14-core CPU) | no configuration | — |
| M4 Max (16-core CPU) | 128 GB | 156 tok/s |
| M5 | no configuration | — |
| M5 Prounverified | no configuration | — |
| M5 Maxunverified | 128 GB | 178 tok/s |