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 ↓
8571 M4 (10c) 16 GB Qwen3.5-9B 4bit 1k 223.7 19.6 26-03-08
8572 M1 Max (32c) 64 GB Qwen3.5-35B-A3B 4bit 64k 411.3 18.9 26-03-08
8573 M3 Ultra (60c) 96 GB Qwen3.5-122B-A10B 4bit 64k 458.6 15.5 26-03-08
8574 M3 Ultra (60c) 96 GB Qwen3.5-122B-A10B 4bit 16k 670.7 35.9 26-03-08
8575 M3 Ultra (60c) 96 GB Qwen3.5-122B-A10B 4bit 32k 587.5 24.4 26-03-08
8576 M3 Ultra (60c) 96 GB Qwen3.5-122B-A10B 4bit 8k 712.7 47.3 26-03-08
8577 M3 Ultra (60c) 96 GB Qwen3.5-122B-A10B 4bit 4k 714.1 50.9 26-03-08
8578 M3 Ultra (60c) 96 GB Qwen3.5-122B-A10B 4bit 1k 638.7 54.4 26-03-08
8579 M4 (10c) 24 GB Qwen3.5-9B-mxfp4 4bit 4k 169.0 20.7 26-03-08
8580 M4 (10c) 24 GB Qwen3.5-9B-mxfp4 4bit 1k 169.7 21.7 26-03-08
8,718 results · Page 858 of 872