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 ↓
336001 M3 Max (40c) 64 GB Qwen3.5-9B 4bit 4k 763.2 64.7 26-03-10
336002 M1 Max (32c) 64 GB Qwen3.5-35B-A3B 4bit 1k 532.5 63.1 26-03-10
336003 M1 Max (32c) 64 GB Qwen3.5-35B-A3B 4bit 4k 578.8 60.5 26-03-10
336004 M3 Ultra (80c) 512 GB GLM-4.7-8bit-gs32 8bit 32k 110.7 6.6 26-03-10
336005 M3 Ultra (80c) 512 GB GLM-4.7-8bit-gs32 8bit 8k 189.4 10.9 26-03-10
336006 M3 Ultra (80c) 512 GB GLM-4.7-8bit-gs32 8bit 16k 157.1 8.9 26-03-10
336007 M3 Ultra (80c) 512 GB GLM-4.7-8bit-gs32 8bit 1k 188.8 13.4 26-03-10
336008 M3 Ultra (80c) 512 GB GLM-4.7-8bit-gs32 8bit 4k 212.6 12.2 26-03-10
336009 M3 Max (40c) 64 GB Qwen3.5-9B 4bit 1k 744.1 68.0 26-03-10
336010 M3 Max (40c) 64 GB Qwen3.5-9B 4bit 4k 761.4 65.4 26-03-10
338,374 results · Page 33601 of 33838