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 ↓
10491 M2 Ultra (60c) 64 GB Qwen3-Coder-Next 4bit 32k 734.9 39.5 26-03-09
10492 M3 Ultra (60c) 96 GB Qwen3.5-0.8B9bit 8bit 64k 4,818 122.4 26-03-09
10493 M3 Ultra (60c) 96 GB Qwen3.5-0.8B9bit 8bit 1k 2,898 301.0 26-03-09
10494 M1 Max (32c) 32 GB Qwen3.5-9B 8bit 64k 220.1 15.6 26-03-09
10495 M1 Max (32c) 32 GB Qwen3.5-9B 8bit 32k 288.6 22.5 26-03-09
10496 M1 Max (32c) 32 GB Qwen3.5-9B 8bit 16k 310.1 28.3 26-03-09
10497 M1 Max (32c) 32 GB Qwen3.5-9B 8bit 8k 316.4 31.9 26-03-09
10498 M1 Max (32c) 32 GB Qwen3.5-9B 8bit 4k 318.6 34.5 26-03-09
10499 M1 Max (32c) 32 GB Qwen3.5-9B 8bit 1k 314.9 35.4 26-03-09
10500 M4 (10c) 16 GB Qwen3.5-VL-4B-4bitCRACK 4bit 4k 373.3 29.3 26-03-09
11,308 results · Page 1050 of 1131