Skip to content
llm-speed
Leaderboard/showdown

M3 Max vs M4 Max

A single shareable card for the M3 Max vs M4 Max matchup. Numbers are the best decode tok/s submitted on the llm-speed suite — every side links back to the run it came from.

M3 Max vs M4 Max

Best decode tok/s across every model submitted on each rig.

Apple M3 · up to 128 GB unified
tok/s
decode (best submitted run)
no submitted run yet
Apple M4 · up to 128 GB unified
tok/s
decode (best submitted run)
no submitted run yet
At least one side has no submitted data — the gap above is what we know so far. Run the suite on the missing side to fill it in.

Want to fill the gap?

One side of this matchup has no submitted run yet. Run the suite and the next refresh of this page will show your number — with the run id linked.

$ pipx install llm-speed && llm-speed bench

Need the long-form table? Open the M3 Max vs M4 Max comparison for every overlapping (model × hardware) row, source runs, and methodology.