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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 66411 | M4 (10c) | 16 GB | Qwen3.5-9B | 4bit | 4k | 224.0 | 20.0 | 26-03-10 |
| 66412 | M4 (10c) | 16 GB | Qwen3.5-9B | 4bit | 1k | 223.4 | 20.3 | 26-03-10 |
| 66413 | M1 Max (32c) | 64 GB | Qwen3.5-0.8B | 4bit | 4k | 2,211 | 174.9 | 26-03-10 |
| 66414 | M1 Max (32c) | 64 GB | Qwen3.5-0.8B | 4bit | 1k | 805.6 | 87.6 | 26-03-10 |
| 66415 | M3 Ultra (80c) | 512 GB | GLM-4.7-8bit-gs32 | 8bit | 4k | 234.9 | 12.2 | 26-03-10 |
| 66416 | M3 Ultra (80c) | 512 GB | GLM-4.7-8bit-gs32 | 8bit | 1k | 220.4 | 13.4 | 26-03-10 |
| 66417 | M4 Pro (16c) | 24 GB | Llama-3.2-3B-Instruct | 8bit | 4k | 795.9 | 52.0 | 26-03-10 |
| 66418 | M4 Pro (16c) | 24 GB | Llama-3.2-3B-Instruct | 8bit | 1k | 818.6 | 60.0 | 26-03-10 |
| 66419 | M4 (10c) | 16 GB | Qwen3.5-9B | 4bit | 1k | 224.3 | 21.1 | 26-03-10 |
| 66420 | M3 Max (40c) | 64 GB | Qwen3.5-27B | 4bit | 1k | 214.8 | 22.8 | 26-03-10 |