← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Pro (20c) · 64 GB · 4bit · 2026-05-16

Performance

32k

tokens

1,802

PP tok/s

50.5

TG tok/s

18182

TTFT (ms)

16.0

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	1,802	50.5	16.0 GB	current
64k	1,375	37.0	18.5 GB	view
128k	836.0	20.6	22.7 GB	view