← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Ultra (60c) · 96 GB · 8bit · 2026-04-26

Performance

1k

tokens

1,278

PP tok/s

79.8

TG tok/s

801

TTFT (ms)

26.4

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.7

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,278	79.8	26.4 GB	current
4k	1,637	71.2	26.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	79.8	1.00×
2×	120.4	1.51×
4×	161.9	2.03×