← Back to community benchmarks

gemma-4-31b-it

M3 Ultra (60c) · 256 GB · 8bit · 2026-04-19

Performance

1k

tokens

245.0

PP tok/s

18.3

TG tok/s

4179

TTFT (ms)

31.8

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	18.3	1.00×
2×	30.9	1.69×