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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 335921 | M4 Pro (20c) | 64 GB | Qwen3.5-9B | unknown | 1k | 308.6 | 2.9 | 26-03-10 |
| 335922 | M3 Ultra (80c) | 512 GB | GLM-4.7-8bit-gs32 | 8bit | 8k | 216.9 | 10.8 | 26-03-10 |
| 335923 | M3 Ultra (80c) | 512 GB | GLM-4.7-8bit-gs32 | 8bit | 1k | 221.9 | 13.3 | 26-03-10 |
| 335924 | M3 Ultra (80c) | 512 GB | GLM-4.7-8bit-gs32 | 8bit | 4k | 236.0 | 12.1 | 26-03-10 |
| 335925 | M2 Pro (19c) | 32 GB | Qwen3.5-35B-A3B | 4bit | 4k | 380.1 | 53.1 | 26-03-10 |
| 335926 | M2 Pro (19c) | 32 GB | Qwen3.5-35B-A3B | 4bit | 1k | 370.1 | 55.9 | 26-03-10 |
| 335927 | M4 (10c) | 16 GB | Llama-3.2-3B-Instruct | 4bit | 1k | 547.3 | 46.3 | 26-03-10 |
| 335928 | M4 (10c) | 16 GB | Llama-3.2-3B-Instruct | 4bit | 4k | 507.6 | 38.2 | 26-03-10 |
| 335929 | M4 (10c) | 32 GB | Qwen3.5-0.8B | 4bit | 4k | 1,470 | 112.8 | 26-03-10 |
| 335930 | M4 (10c) | 32 GB | Qwen3.5-0.8B | 4bit | 1k | 1,491 | 127.5 | 26-03-10 |