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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 291 | M4 (10c) | 16 GB | Qwen3-VL-Embedding-2B | 4bit | 1k | 870.4 | 81.5 | 26-03-10 |
| 292 | M4 Pro (20c) | 64 GB | Qwen3.5-35B-A3B | 8bit | 4k | 888.2 | 54.1 | 26-03-10 |
| 293 | M4 Pro (20c) | 64 GB | Qwen3.5-35B-A3B | 8bit | 1k | 868.5 | 56.2 | 26-03-10 |
| 294 | M1 Max (32c) | 64 GB | GLM-4.7-Flash | 4bit | 4k | 395.5 | 37.0 | 26-03-10 |
| 295 | M1 Max (32c) | 64 GB | GLM-4.7-Flash | 4bit | 1k | 397.5 | 42.7 | 26-03-10 |
| 296 | M4 (10c) | 16 GB | Qwen3-VL-Embedding-2B | 4bit | 4k | 744.7 | 59.5 | 26-03-10 |
| 297 | M4 (10c) | 16 GB | Qwen3-VL-Embedding-2B | 4bit | 1k | 818.5 | 63.9 | 26-03-10 |
| 298 | M1 Max (32c) | 64 GB | Qwen3.5-35B-A3B | 8bit | 4k | 572.8 | 46.8 | 26-03-10 |
| 299 | M1 Max (32c) | 64 GB | Qwen3.5-35B-A3B | 8bit | 1k | 523.0 | 50.0 | 26-03-10 |
| 300 | M4 (10c) | 24 GB | Qwen3.5-4B | 4bit | 4k | 406.9 | 37.5 | 26-03-10 |