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 ↓
6721 M1 Max (32c) 64 GB Qwen3.5-35B-A3B 6bit 4k 558.7 49.0 26-03-09
6722 M1 Max (32c) 64 GB Qwen3.5-35B-A3B 4bit 1k 540.2 63.7 26-03-09
6723 M1 Max (32c) 64 GB Qwen3.5-35B-A3B 4bit 4k 585.0 60.1 26-03-09
6724 M1 Max (32c) 64 GB Qwen3.5-9B 8bit 1k 304.3 35.6 26-03-09
6725 M1 Max (32c) 64 GB Qwen3.5-9B 8bit 4k 319.1 34.7 26-03-09
6726 M3 Ultra (80c) 512 GB GLM-5-4.8bit 4bit 32k 73.2 12.3 26-03-09
6727 M3 Ultra (80c) 512 GB GLM-5-4.8bit 4bit 16k 119.8 13.0 26-03-09
6728 M3 Ultra (80c) 512 GB GLM-5-4.8bit 4bit 8k 156.3 13.5 26-03-09
6729 M3 Ultra (80c) 512 GB GLM-5-4.8bit 4bit 4k 182.6 13.7 26-03-09
6730 M3 Ultra (80c) 512 GB GLM-5-4.8bit 4bit 1k 188.7 16.6 26-03-09
6,907 results · Page 673 of 691