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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 43531 | M1 Max (32c) | 64 GB | Qwen3.5-0.8B | 4bit | 1k | 805.6 | 87.6 | 26-03-10 |
| 43532 | M3 Ultra (80c) | 512 GB | GLM-4.7-8bit-gs32 | 8bit | 4k | 234.9 | 12.2 | 26-03-10 |
| 43533 | M3 Ultra (80c) | 512 GB | GLM-4.7-8bit-gs32 | 8bit | 1k | 220.4 | 13.4 | 26-03-10 |
| 43534 | M4 Pro (16c) | 24 GB | Llama-3.2-3B-Instruct | 8bit | 4k | 795.9 | 52.0 | 26-03-10 |
| 43535 | M4 Pro (16c) | 24 GB | Llama-3.2-3B-Instruct | 8bit | 1k | 818.6 | 60.0 | 26-03-10 |
| 43536 | M4 (10c) | 16 GB | Qwen3.5-9B | 4bit | 1k | 224.3 | 21.1 | 26-03-10 |
| 43537 | M3 Max (40c) | 64 GB | Qwen3.5-27B | 4bit | 1k | 214.8 | 22.8 | 26-03-10 |
| 43538 | M3 Max (40c) | 64 GB | Qwen3.5-27B | 4bit | 4k | 215.9 | 21.6 | 26-03-10 |
| 43539 | M5 (10c) | 32 GB | Qwen3.5-35B-A3B | 4bit | 4k | 490.6 | 59.3 | 26-03-10 |
| 43540 | M5 (10c) | 32 GB | Qwen3.5-35B-A3B | 4bit | 1k | 479.5 | 61.6 | 26-03-10 |