Skip to content
llm-speed
Leaderboard/model/anthropic-claude-haiku-4-5

claude-haiku-4.5

1 workload result across 1 hardware configuration.

Fastest known config

45.1 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-api45.09tok/s143.9tok/s820msr_fui3jk1m4n0

claude-haiku-4.5 on hardware