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 ↓ |
|---|---|---|---|---|---|---|---|---|
| 322431 | M4 (10c) | 32 GB | GLM-4.7-Flash | 4bit | 4k | 277.7 | 29.6 | 26-03-10 |
| 322432 | M4 (10c) | 32 GB | GLM-4.7-Flash | 4bit | 1k | 326.7 | 36.5 | 26-03-10 |
| 322433 | M4 Pro (16c) | 24 GB | gpt-oss-20b-MXFP4-Q8 | 4bit | 4k | 498.0 | 54.5 | 26-03-10 |
| 322434 | M4 Pro (16c) | 24 GB | gpt-oss-20b-MXFP4-Q8 | 4bit | 1k | 430.6 | 66.6 | 26-03-10 |
| 322435 | M4 (10c) | 16 GB | Qwen3.5-9B | 4bit | 1k | 215.4 | 19.2 | 26-03-10 |
| 322436 | M4 Max (40c) | 128 GB | Qwen3.5-35B-A3B-Hereticmx... | 8bit | 4k | 1,690 | 79.3 | 26-03-10 |
| 322437 | M4 Max (40c) | 128 GB | Qwen3.5-35B-A3B-Hereticmx... | 8bit | 1k | 1,625 | 85.0 | 26-03-10 |
| 322438 | M4 (10c) | 24 GB | Llama-3.2-1B-Instruct | 4bit | 1k | 1,525 | 119.6 | 26-03-10 |
| 322439 | M4 (10c) | 24 GB | Qwen3-VL-4B-Instruct | 4bit | 8k | 283.5 | 23.8 | 26-03-10 |
| 322440 | M4 (10c) | 24 GB | Qwen3-VL-4B-Instruct | 4bit | 1k | 357.2 | 36.1 | 26-03-10 |