gpt-4o-mini

on M3 Pro

158

tok/sdecode

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

rank in tier

5/27M3 Pro runstop 19%

best workload

chat-short

where the rig flew

slowest workload

—

single-workload run

backend

hosted-apiHosted API — the number is your network + the provider's rig, not yours.

faster than

gpt-oss-20b-MXFP4-Q4 on M3 Ultra153 tok/s
Qwen2.5-7B-Instruct-4bit on M3 Ultra140 tok/s
Qwen2.5-Coder-7B-Instruct-4bit on M3 Ultra139 tok/s

This is a shareable view of one signed llm-speed suite-suite-v1 run. Numbers are not edited. The raw record has every workload, the public key, and the fingerprint hash.