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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 155321 | M3 Ultra (80c) | 512 GB | Qwen3.6-35B-A3B | 8bit | 16k | 1,234 | 270.0 | 26-04-28 |
| 155322 | M3 Ultra (80c) | 512 GB | Qwen3.6-35B-A3B | 8bit | 4k | 1,982 | 295.3 | 26-04-28 |
| 155323 | M3 Ultra (80c) | 512 GB | Qwen3.6-35B-A3B | 8bit | 1k | 2,240 | 324.3 | 26-04-28 |
| 155324 | M4 Pro (16c) | 24 GB | Qwen3.5-9Bvlm | 4bit | 1k | 342.0 | 52.2 | 26-04-28 |
| 155325 | M4 Pro (16c) | 24 GB | Qwen3.5-9Bvlm | 4bit | 4k | 354.2 | 50.5 | 26-04-28 |
| 155326 | M5 (10c) | 32 GB | Qwen2.5-Coder-7B-Instruct | 4bit | 4k | 787.1 | 27.1 | 26-04-28 |
| 155327 | M5 (10c) | 32 GB | Qwen2.5-Coder-7B-Instruct | 4bit | 1k | 714.4 | 27.2 | 26-04-28 |
| 155328 | M5 (10c) | 32 GB | Nemotron-Cascade-2-30B-A3... | 3bit | 32k | 900.3 | 32.4 | 26-04-28 |
| 155329 | M5 (10c) | 32 GB | Nemotron-Cascade-2-30B-A3... | 3bit | 16k | 953.1 | 44.6 | 26-04-28 |
| 155330 | M5 (10c) | 32 GB | Nemotron-Cascade-2-30B-A3... | 3bit | 8k | 960.3 | 51.2 | 26-04-28 |