← Back to community benchmarks

gemma-4-31b-it

M3 Ultra (60c) · 96 GB · 4bit · 2026-05-18

Performance

1k

tokens

245.4

PP tok/s

31.2

TG tok/s

4174

TTFT (ms)

17.6

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	245.4	31.2	17.6 GB	current
4k	252.4	30.1	20.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	31.2	1.00×
2×	47.4	1.52×
4×	54.2	1.74×