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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 322411 | M4 (10c) | 16 GB | Qwen3.5-9B | 4bit | 4k | 220.8 | 19.7 | 26-03-10 |
| 322412 | M1 Pro (14c) | 16 GB | Qwen3.5-9B | 4bit | 4k | 137.4 | 28.7 | 26-03-10 |
| 322413 | M1 Pro (14c) | 16 GB | Qwen3.5-9B | 4bit | 1k | 136.5 | 29.8 | 26-03-10 |
| 322414 | M3 Max (40c) | 128 GB | Qwen3.5-9B | 8bit | 4k | 752.3 | 38.4 | 26-03-10 |
| 322415 | M3 Max (40c) | 128 GB | Qwen3.5-9B | 8bit | 1k | 728.1 | 39.6 | 26-03-10 |
| 322416 | M3 Ultra (60c) | 96 GB | Qwen3.5-35B-A3B | unknown | 1k | 141.4 | 0.5 | 26-03-10 |
| 322417 | M4 (10c) | 16 GB | Qwen3.5-9B | 4bit | 1k | 218.2 | 19.8 | 26-03-10 |
| 322418 | M4 (10c) | 16 GB | Qwen3.5-4B | 4bit | 1k | 359.9 | 38.4 | 26-03-10 |
| 322419 | M4 (10c) | 16 GB | Qwen3.5-4B | 4bit | 1k | 409.8 | 38.1 | 26-03-10 |
| 322420 | M2 Ultra (60c) | 64 GB | Qwen3.5-35B-A3B | 8bit | 4k | 1,051 | 65.4 | 26-03-10 |