← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Max (40c) · 128 GB · 4bit · 2026-05-20

Performance

32k

tokens

2,784

PP tok/s

79.5

TG tok/s

11770

TTFT (ms)

16.5

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9rc1

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	2,567	111.0	14.9 GB	view
8k	3,658	105.6	15.1 GB	view
16k	3,165	94.4	15.6 GB	view
32k	2,784	79.5	16.5 GB	current
64k	2,110	55.6	18.5 GB	view
128k	1,230	32.9	22.7 GB	view
195k	372.7	7.9	27.7 GB	view