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 ↓
65781 M2 Max (38c) 96 GB Llama-3.3-70B-Instruct 4bit 4k 64.7 7.7 26-03-10
65782 M2 Max (38c) 96 GB Llama-3.3-70B-Instruct 4bit 1k 72.7 8.6 26-03-10
65783 M4 Max (40c) 128 GB Huihui-Qwen3-Next-80B-A3B... 4bit 4k 1,300 85.9 26-03-10
65784 M4 Max (40c) 128 GB Huihui-Qwen3-Next-80B-A3B... 4bit 1k 1,044 89.2 26-03-10
65785 M4 (10c) 16 GB Qwen3.5-4B 4bit 4k 399.5 32.5 26-03-10
65786 M4 (10c) 16 GB Qwen3.5-4B 4bit 1k 402.8 34.5 26-03-10
65787 M3 Ultra (60c) 96 GB Qwen3.5-4B unknown 1k 986.8 17.3 26-03-10
65788 M4 (10c) 16 GB Qwen3.5-4B 4bit 1k 396.8 34.3 26-03-10
65789 M4 (10c) 32 GB Qwen3.5-4B 4bit 4k 404.6 35.0 26-03-10
65790 M4 (10c) 32 GB Qwen3.5-4B 4bit 1k 405.6 38.3 26-03-10
67,855 results · Page 6579 of 6786