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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 65951 | M3 Ultra (80c) | 512 GB | Qwen3-Coder-Next | 8bit | 1k | 1,245 | 61.1 | 26-03-10 |
| 65952 | M4 Max (40c) | 128 GB | Qwen3.5-122B-A10B | 4bit | 32k | 313.4 | 21.7 | 26-03-10 |
| 65953 | M4 Max (40c) | 128 GB | Qwen3.5-122B-A10B | 4bit | 64k | 237.6 | 13.3 | 26-03-10 |
| 65954 | M4 Max (40c) | 128 GB | Qwen3.5-122B-A10B | 4bit | 16k | 344.8 | 30.8 | 26-03-10 |
| 65955 | M4 Max (40c) | 128 GB | Qwen3.5-122B-A10B | 4bit | 4k | 422.0 | 44.3 | 26-03-10 |
| 65956 | M4 Max (40c) | 128 GB | Qwen3.5-122B-A10B | 4bit | 8k | 356.5 | 42.7 | 26-03-10 |
| 65957 | M4 Max (40c) | 128 GB | Qwen3.5-122B-A10B | 4bit | 1k | 554.6 | 52.6 | 26-03-10 |
| 65958 | M1 Max (32c) | 64 GB | Qwen3-Coder-Next | 4bit | 1k | 378.5 | 46.9 | 26-03-10 |
| 65959 | M1 Max (32c) | 64 GB | Qwen3-Coder-Next | 4bit | 4k | 426.2 | 44.6 | 26-03-10 |
| 65960 | M2 Pro (19c) | 16 GB | Qwen3.5-0.8B | unknown | 4k | 2,078 | 23.3 | 26-03-10 |