← Back to community benchmarks

gemma-4-31B-it

M2 Ultra (60c) · 192 GB · 8bit · 2026-05-15

Performance

4k

tokens

146.6

PP tok/s

16.2

TG tok/s

27937

TTFT (ms)

34.5

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 192 GB

GPU Cores 60

Software

oMLX v0.3.9.dev2

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	145.5	16.8	31.8 GB	view
4k	146.6	16.2	34.5 GB	current