Community Benchmarks

Download oMLX →

Real performance numbers from oMLX users around the world. Submit yours from the app (v0.2.6+).

Reset filters
# Chip RAM Model Quant Ctx PP tok/s TG tok/s Date ↓
11 M3 Ultra (60c) 256 GB Qwen3.5-122B-A10B 4bit 64k 474.8 40.5 26-07-22
12 M1 Max (32c) 32 GB Ternary-Bonsai-27B 2bit 64k 111.9 12.5 26-07-22
13 M4 Max (40c) 64 GB gemma-4-26b-a4b-it 8bit 64k 804.9 45.1 26-07-22
14 M4 Max (40c) 64 GB Qwen3.6-35B-A3B 4bit 64k 1,012 75.8 26-07-22
15 M5 Max (40c) 128 GB Laguna-XS-2.1 8bit 64k 1,505 64.5 26-07-22
16 M5 Pro (20c) 64 GB gemma-4-e4b-it-qat-OptiQ 4bit 64k 2,917 38.1 26-07-22
17 M4 Max (40c) 64 GB Qwen3.6-35B-A3B 4bit 64k 984.2 76.3 26-07-22
18 M4 Max (40c) 64 GB Qwen3.6-35B-A3B 8bit 64k 832.9 60.6 26-07-22
19 M3 Ultra (60c) 256 GB gemma-4-31B-it-qat-OptiQ 4bit 64k 181.1 15.7 26-07-22
20 M4 Max (32c) 36 GB gemma-4-e4b-it 4bit 64k 1,283 47.2 26-07-22
13,014 results · Page 2 of 1302