← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Pro (16c) · 48 GB · 4bit · 2026-05-08

Performance

8k

tokens

1,806

PP tok/s

67.1

TG tok/s

4537

TTFT (ms)

15.1

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,276	73.9	14.3 GB	view
4k	1,721	70.9	15.0 GB	view
8k	1,806	67.1	15.1 GB	current
16k	1,767	61.3	15.6 GB	view
32k	1,594	52.2	16.5 GB	view
64k	1,257	40.4	18.5 GB	view