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 ↓
40001 M2 Ultra (76c) 128 GB Qwen3.5-4B 8bit 8k 1,421 90.1 26-03-09
40002 M2 Ultra (76c) 128 GB Qwen3.5-4B 8bit 16k 1,362 80.1 26-03-09
40003 M2 Ultra (76c) 128 GB Qwen3.5-4B 8bit 4k 1,448 96.2 26-03-09
40004 M2 Ultra (76c) 128 GB Qwen3.5-4B 8bit 1k 1,423 99.9 26-03-09
40005 M4 (10c) 24 GB Llama-3.2-3B-Instruct 4bit 1k 520.4 45.2 26-03-09
40006 M4 (10c) 24 GB Llama-3.2-3B-Instruct 4bit 4k 478.6 37.0 26-03-09
40007 M4 (10c) 24 GB Qwen3.5-4B 4bit 4k 380.6 34.1 26-03-09
40008 M4 (10c) 24 GB Qwen3.5-4B 4bit 1k 378.3 35.1 26-03-09
40009 M2 Ultra (76c) 128 GB Qwen3.5-0.8B bf16 64k 4,660 83.2 26-03-09
40010 M4 (10c) 16 GB Qwen3.5-4B 4bit 1k 400.3 38.8 26-03-09
40,214 results · Page 4001 of 4022