← Back to community benchmarks

gemma-4-26B-A4B-it

M3 Ultra (80c) · 512 GB · 8bit · 2026-05-08

Performance

32k

tokens

1,942

PP tok/s

57.9

TG tok/s

16876

TTFT (ms)

28.2

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	2,122	68.7	26.9 GB	view
32k	1,942	57.9	28.2 GB	current
64k	1,579	42.9	29.2 GB	view