Skip to content
llm-speed
Leaderboard/model/qwen2-5-72b-instruct-4bit

qwen2.5-72b-Instruct-4bit

1 workload result across 1 hardware configuration.

Fastest known config

16.3 decode tok/s

on M3 Ultra (60-core GPU) + 96GB unified via mlx see full run

M3 Ultra (60-core GPU) + 96GB unifiedM3 Ultra (60-core GPU) + 96GB unified

WorkloadBackendQuantdecode tok/sprefill tok/sTTFTRun
chat-shortmlx@0.31.316.31tok/s23.25tok/s5,635msr_5c80gthqlh6

qwen2.5-72b-Instruct-4bit on hardware