← Back to community benchmarks

gemma-4-31b-it-oQ5

M5 Max (40c) · 128 GB · 5bit · 2026-05-26

Performance

1k

tokens

272.9

PP tok/s

11.7

TG tok/s

3753

TTFT (ms)

21.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.11

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	272.9	11.7	21.8 GB	current
4k	346.1	12.4	23.9 GB	view
8k	386.9	12.3	25.9 GB	view
16k	364.4	11.0	26.3 GB	view
32k	298.3	8.2	29.1 GB	view
64k	233.4	6.8	35.0 GB	view