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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 286161 | M3 Max (40c) | 64 GB | Qwen3.5-9B | 4bit | 1k | 570.7 | 57.2 | 26-03-11 |
| 286162 | M1 Max (32c) | 64 GB | Qwen3.5-35B-A3B | 4bit | 64k | 372.2 | 19.2 | 26-03-11 |
| 286163 | M1 Max (32c) | 64 GB | Qwen3.5-35B-A3B | 4bit | 32k | 476.4 | 31.0 | 26-03-11 |
| 286164 | M1 Max (32c) | 64 GB | Qwen3.5-35B-A3B | 4bit | 16k | 527.4 | 42.0 | 26-03-11 |
| 286165 | M1 Max (32c) | 64 GB | Qwen3.5-35B-A3B | 4bit | 8k | 554.2 | 51.4 | 26-03-11 |
| 286166 | M1 Max (32c) | 64 GB | Qwen3.5-35B-A3B | 4bit | 4k | 563.6 | 57.7 | 26-03-11 |
| 286167 | M1 Max (32c) | 64 GB | Qwen3.5-35B-A3B | 4bit | 1k | 537.5 | 59.6 | 26-03-11 |
| 286168 | M3 Max (40c) | 64 GB | glm4_flash | 4bit | 16k | 464.2 | 39.6 | 26-03-11 |
| 286169 | M3 Max (40c) | 64 GB | glm4_flash | 4bit | 8k | 726.2 | 50.8 | 26-03-11 |
| 286170 | M3 Max (40c) | 64 GB | glm4_flash | 4bit | 4k | 925.6 | 59.7 | 26-03-11 |