← Back to community benchmarks

gemma-4-31B-it-TurboQuant

M2 Pro (16c) · 32 GB · 4bit · 2026-04-17

Performance

1k

tokens

40.8

PP tok/s

8.7

TG tok/s

25128

TTFT (ms)

17.6

Peak mem (GB)

Hardware

Chip M2 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.3.6

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	40.8	8.7	17.6 GB	current
4k	40.0	6.9	19.3 GB	view
8k	34.8	2.1	19.6 GB	view