Skip to content
llm-speed
Leaderboard/model/llama-4-maverick

llama-4-maverick

1 workload result across 1 hardware configuration.

Fastest known config

125.5 decode tok/s

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

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

WorkloadBackendQuantdecode tok/sprefill tok/sTTFTRun
chat-shorthosted-api125.5tok/s272.4tok/s646msr_u0yt9c4ntxa

llama-4-maverick on hardware