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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 53351 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 16k | 412.9 | 38.1 | 26-03-08 |
| 53352 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 8k | 427.1 | 46.1 | 26-03-08 |
| 53353 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 4k | 443.4 | 50.2 | 26-03-08 |
| 53354 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 1k | 464.3 | 53.4 | 26-03-08 |
| 53355 | M2 Max (38c) | 96 GB | gpt-oss-120b | 4bit | 32k | 165.3 | 14.6 | 26-03-08 |
| 53356 | M2 Max (38c) | 96 GB | gpt-oss-120b | 4bit | 16k | 177.1 | 22.7 | 26-03-08 |
| 53357 | M2 Max (38c) | 96 GB | gpt-oss-120b | 4bit | 8k | 183.9 | 37.1 | 26-03-08 |
| 53358 | M2 Max (38c) | 96 GB | gpt-oss-120b | 4bit | 4k | 182.0 | 44.7 | 26-03-08 |
| 53359 | M2 Max (38c) | 96 GB | gpt-oss-120b | 4bit | 1k | 187.7 | 54.9 | 26-03-08 |
| 53360 | M3 Ultra (80c) | 512 GB | Qwen3.5-27B-Claude-4.6-Op... | 6bit | 32k | 370.0 | 19.5 | 26-03-08 |