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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 71311 | M3 Max (40c) | 128 GB | NVIDIA-Nemotron-3-Nano-30... | 8bit | 128k | 496.7 | 31.9 | 26-05-15 |
| 71312 | M3 Max (40c) | 128 GB | NVIDIA-Nemotron-3-Nano-30... | 8bit | 64k | 688.4 | 43.2 | 26-05-15 |
| 71313 | M3 Max (40c) | 128 GB | NVIDIA-Nemotron-3-Nano-30... | 8bit | 32k | 772.9 | 50.1 | 26-05-15 |
| 71314 | M3 Max (40c) | 128 GB | NVIDIA-Nemotron-3-Nano-30... | 8bit | 16k | 808.3 | 52.3 | 26-05-15 |
| 71315 | M3 Max (40c) | 128 GB | NVIDIA-Nemotron-3-Nano-30... | 8bit | 8k | 842.1 | 54.8 | 26-05-15 |
| 71316 | M3 Max (40c) | 128 GB | NVIDIA-Nemotron-3-Nano-30... | 8bit | 1k | 673.7 | 59.7 | 26-05-15 |
| 71317 | M3 Max (40c) | 128 GB | NVIDIA-Nemotron-3-Nano-30... | 8bit | 4k | 831.0 | 58.0 | 26-05-15 |
| 71318 | M4 (10c) | 16 GB | Qwen3.5-9B | 4bit | 1k | 216.3 | 20.7 | 26-05-15 |
| 71319 | M1 Ultra (48c) | 64 GB | gemma-4-31b-it | 4bit | 4k | 105.7 | 17.7 | 26-05-15 |
| 71320 | M1 Ultra (48c) | 64 GB | gemma-4-31b-it | 4bit | 1k | 105.1 | 16.7 | 26-05-15 |