Community Benchmarks
Download oMLX →Real performance numbers from oMLX users around the world. Submit yours from the app (v0.2.6+).
| # | Chip | RAM | Model | Quant | Ctx | PP tok/s | TG tok/s | Date ↓ |
|---|---|---|---|---|---|---|---|---|
| 16921 | M3 Ultra (80c) | 512 GB | gpt-oss-120b | 8bit | 4k | 631.9 | 54.2 | 26-03-08 |
| 16922 | M3 Ultra (80c) | 512 GB | gpt-oss-120b | 8bit | 1k | 569.3 | 60.7 | 26-03-08 |
| 16923 | M3 Ultra (80c) | 512 GB | Qwen3.5-122B-A10B | 4bit | 1k | 904.5 | 52.5 | 26-03-08 |
| 16924 | M3 Ultra (80c) | 512 GB | Qwen3.5-122B-A10B | 4bit | 4k | 951.6 | 52.0 | 26-03-08 |
| 16925 | M5 (10c) | 24 GB | Qwen3.5-9B-mxfp4 | 4bit | 4k | 214.5 | 25.3 | 26-03-08 |
| 16926 | M5 (10c) | 24 GB | Qwen3.5-9B-mxfp4 | 4bit | 1k | 215.4 | 26.1 | 26-03-08 |
| 16927 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 32k | 379.4 | 25.5 | 26-03-08 |
| 16928 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 16k | 412.9 | 38.1 | 26-03-08 |
| 16929 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 8k | 427.1 | 46.1 | 26-03-08 |
| 16930 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 4k | 443.4 | 50.2 | 26-03-08 |