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 ↓
207131 M5 Max (40c) 128 GB NVIDIA-Nemotron-3-Nano-30... 6bit 16k 3,286 116.3 26-04-18
207132 M5 Max (40c) 128 GB NVIDIA-Nemotron-3-Nano-30... 6bit 1k 2,478 131.6 26-04-18
207133 M5 Max (40c) 128 GB NVIDIA-Nemotron-3-Nano-30... 6bit 4k 2,840 123.1 26-04-18
207134 M1 Max (32c) 32 GB Qwen3.6-35B-A3B 4bit 4k 565.8 62.7 26-04-18
207135 M1 Max (32c) 32 GB Qwen3.6-35B-A3B 4bit 1k 454.5 56.8 26-04-18
207136 M5 Pro (16c) 48 GB Qwen3.6-35B-A3B 4bit 4k 1,787 94.6 26-04-18
207137 M5 Pro (16c) 48 GB Qwen3.6-35B-A3B 4bit 1k 1,196 99.5 26-04-18
207138 M4 Max (32c) 36 GB Qwen3.5-27B-Claude-4.6-Op... 6bit 1k 190.3 15.8 26-04-18
207139 M4 Max (32c) 36 GB Qwen3.5-27B-Claude-4.6-Op... 6bit 4k 196.5 15.4 26-04-18
207140 M4 Pro (20c) 64 GB Qwen3.6-35B-A3B 4bit 4k 905.7 80.4 26-04-18
314,155 results · Page 20714 of 31416