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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 4011 | M4 Pro (20c) | 64 GB | GLM-4.7-Flash | 6bit | 4k | 546.4 | 42.5 | 26-03-09 |
| 4012 | M4 Pro (20c) | 64 GB | GLM-4.7-Flash | 6bit | 1k | 608.4 | 49.8 | 26-03-09 |
| 4013 | M1 Max (32c) | 64 GB | Qwen3.5-9B | 4bit | 4k | 311.9 | 53.2 | 26-03-09 |
| 4014 | M1 Max (32c) | 64 GB | Qwen3.5-9B | 4bit | 1k | 308.2 | 55.1 | 26-03-09 |
| 4015 | M4 Pro (20c) | 64 GB | Qwen3-Coder-Next | 4bit | 4k | 660.7 | 60.6 | 26-03-09 |
| 4016 | M4 Pro (20c) | 64 GB | Qwen3-Coder-Next | 4bit | 1k | 574.9 | 64.4 | 26-03-09 |
| 4017 | M4 Pro (20c) | 48 GB | Qwen3.5-4B | 4bit | 32k | 655.0 | 49.9 | 26-03-09 |
| 4018 | M4 Pro (20c) | 48 GB | Qwen3.5-4B | 4bit | 64k | 534.5 | 36.3 | 26-03-09 |
| 4019 | M4 Pro (20c) | 48 GB | Qwen3.5-4B | 4bit | 8k | 781.9 | 72.4 | 26-03-09 |
| 4020 | M4 Pro (20c) | 48 GB | Qwen3.5-4B | 4bit | 16k | 737.3 | 62.8 | 26-03-09 |