← Back to community benchmarks

gemma-4-31b-it

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-07

Performance

32k

tokens

224.1

PP tok/s

15.0

TG tok/s

146202

TTFT (ms)

41.9

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	205.5	18.2	36.4 GB	view
8k	248.6	17.7	37.9 GB	view
16k	240.5	16.7	39.0 GB	view
32k	224.1	15.0	41.9 GB	current
64k	194.2	12.5	47.9 GB	view
128k	149.9	4.4	60.7 GB	view