Skip to content
llm-speed
Leaderboard/model/gemma-2-9b-it-4bit

gemma-2-9b-it-4bit

1 workload result across 1 hardware configuration.

Fastest known config

22.0 decode tok/s

on M3 Pro (18-core GPU) + 36GB unified via mlx see full run

M3 Pro (18-core GPU) + 36GB unifiedM3 Pro (18-core GPU) + 36GB unified

WorkloadBackendQuantdecode tok/sprefill tok/sTTFTRun
chat-shortmlx@0.31.321.97tok/s102.5tok/s1,151msr_q7t7b7dcuz5

gemma-2-9b-it-4bit on hardware