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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 65181 | M4 (10c) | 16 GB | Qwen3.5-VL-4B-8bitCRACK | 8bit | 8k | 389.6 | 19.0 | 26-03-13 |
| 65182 | M4 (10c) | 16 GB | Qwen3.5-VL-4B-8bitCRACK | 8bit | 4k | 401.1 | 20.9 | 26-03-13 |
| 65183 | M4 (10c) | 16 GB | Qwen3.5-VL-4B-8bitCRACK | 8bit | 1k | 396.3 | 21.6 | 26-03-13 |
| 65184 | M4 Max (40c) | 64 GB | NVIDIA-Nemotron-3-Nano-30... | 4bit | 4k | 1,523 | 145.1 | 26-03-13 |
| 65185 | M4 Max (40c) | 64 GB | NVIDIA-Nemotron-3-Nano-30... | 4bit | 1k | 1,136 | 152.2 | 26-03-13 |
| 65186 | M1 (7c) | 16 GB | Qwen3.5-9B | 4bit | 1k | 69.4 | 12.7 | 26-03-13 |
| 65187 | M1 (7c) | 16 GB | Qwen3.5-9B | 4bit | 4k | 69.6 | 12.6 | 26-03-13 |
| 65188 | M1 Max (32c) | 64 GB | Qwen3.5-35B-A3B | 8bit | 64k | 396.7 | 19.3 | 26-03-13 |
| 65189 | M1 Max (32c) | 64 GB | Qwen3.5-35B-A3B | 8bit | 32k | 459.1 | 28.8 | 26-03-13 |
| 65190 | M1 Max (32c) | 64 GB | Qwen3.5-35B-A3B | 8bit | 8k | 531.9 | 37.5 | 26-03-13 |