← Back to community benchmarks

gemma-4-26B-A4B-it-oQ3

M4 (10c) · 32 GB · 3bit · 2026-05-06

Performance

8k

tokens

363.8

PP tok/s

33.1

TG tok/s

22517

TTFT (ms)

12.6

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.8

macOS macOS 26.3.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	363.8	33.1	12.6 GB	current
16k	771.5	12.0	13.5 GB	view
32k	730.1	11.7	14.4 GB	view
64k	590.7	10.9	15.3 GB	view