← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (20c) · 64 GB · 4bit · 2026-05-01

Performance

4k

tokens

1,955

PP tok/s

71.2

TG tok/s

2095

TTFT (ms)

14.9

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,518	75.1	14.3 GB	view
4k	1,955	71.2	14.9 GB	current
8k	2,051	65.4	15.1 GB	view
16k	1,972	59.7	15.6 GB	view
32k	1,810	49.1	16.0 GB	view
64k	1,417	36.0	17.7 GB	view
128k	971.4	23.8	21.2 GB	view