← Back to community benchmarks

gemma-4-31B-it-OptiQ

M2 Ultra (60c) · 64 GB · 4bit · 2026-05-05

Performance

1k

tokens

146.3

PP tok/s

23.9

TG tok/s

7000

TTFT (ms)

19.2

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 64 GB

GPU Cores 60

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	146.3	23.9	19.2 GB	current
4k	146.8	22.7	21.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	23.9	1.00×
2×	29.5	1.23×
4×	32.8	1.37×