Skip to content
llm-speed
Leaderboard/model/deepseek-deepseek-v3-2

deepseek-v3.2

1 workload result across 1 hardware configuration.

Fastest known config

20.0 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-api20.03tok/s57.45tok/s1,932msr_n4t6xaak-jk

deepseek-v3.2 on hardware