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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 39511 | M3 (10c) | 24 GB | Llama-3.2-1B-Instruct | 4bit | 8k | 1,130 | 59.3 | 26-03-09 |
| 39512 | M3 (10c) | 24 GB | Llama-3.2-1B-Instruct | 4bit | 4k | 1,216 | 76.7 | 26-03-09 |
| 39513 | M3 (10c) | 24 GB | Llama-3.2-1B-Instruct | 4bit | 1k | 1,249 | 102.4 | 26-03-09 |
| 39514 | M4 (8c) | 16 GB | Llama-3.2-3B-Instruct | 4bit | 1k | 419.8 | 47.9 | 26-03-09 |
| 39515 | M4 (8c) | 16 GB | Llama-3.2-3B-Instruct | 4bit | 4k | 382.4 | 37.8 | 26-03-09 |
| 39516 | M2 Pro (16c) | 16 GB | Qwen3.5-9B | 8bit | 1k | 171.5 | 20.0 | 26-03-09 |
| 39517 | M2 Pro (16c) | 16 GB | Qwen3.5-9B | 8bit | 4k | 172.3 | 18.1 | 26-03-09 |
| 39518 | M3 Ultra (80c) | 512 GB | Qwen3.5-35B-A3B | 4bit | 1k | 1,681 | 96.0 | 26-03-09 |
| 39519 | M3 Ultra (80c) | 512 GB | Qwen3.5-35B-A3B | 4bit | 4k | 2,425 | 92.2 | 26-03-09 |
| 39520 | M5 (10c) | 24 GB | Qwen3.5-4B | 4bit | 4k | 418.4 | 32.9 | 26-03-09 |