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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 1631 | M2 Ultra (76c) | 192 GB | glm-4.6vmxfp8 | 8bit | 8k | 305.9 | 22.6 | 26-03-08 |
| 1632 | M2 Ultra (76c) | 192 GB | glm-4.6vmxfp8 | 8bit | 1k | 317.9 | 28.2 | 26-03-08 |
| 1633 | M5 (10c) | 24 GB | Qwen3.5-9B-mxfp4 | 4bit | 4k | 214.5 | 25.3 | 26-03-08 |
| 1634 | M5 (10c) | 24 GB | Qwen3.5-9B-mxfp4 | 4bit | 1k | 215.4 | 26.1 | 26-03-08 |
| 1635 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 32k | 379.4 | 25.5 | 26-03-08 |
| 1636 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 16k | 412.9 | 38.1 | 26-03-08 |
| 1637 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 8k | 427.1 | 46.1 | 26-03-08 |
| 1638 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 4k | 443.4 | 50.2 | 26-03-08 |
| 1639 | M2 Max (38c) | 96 GB | Qwen3-Coder-Next | 6bit | 1k | 464.3 | 53.4 | 26-03-08 |
| 1640 | M2 Max (38c) | 96 GB | gpt-oss-120b | 4bit | 32k | 165.3 | 14.6 | 26-03-08 |