← Back to community benchmarks

gemma-4-31B-it

M2 Ultra (60c) · 64 GB · 8bit · 2026-04-23

Performance

4k

tokens

145.7

PP tok/s

14.7

TG tok/s

28122

TTFT (ms)

33.6

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 64 GB

GPU Cores 60

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	144.7	16.5	31.8 GB	view
4k	145.7	14.7	33.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	16.5	1.00×
2×	25.0	1.52×
4×	30.9	1.87×