← Back to community benchmarks

gemma-4-31B-it-TurboQuant

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

Performance

8k

tokens

34.8

PP tok/s

2.1

TG tok/s

235092

TTFT (ms)

19.6

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 8,192

Performance by Context Length

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