← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Pro (18c) · 36 GB · 4bit · 2026-04-17

Performance

8k

tokens

547.4

PP tok/s

33.6

TG tok/s

14965

TTFT (ms)

14.8

Peak mem (GB)

Hardware

Chip M3 Pro (18c)

Memory 36 GB

GPU Cores 18

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	510.0	36.2	14.2 GB	view
4k	540.2	31.8	14.7 GB	view
8k	547.4	33.6	14.8 GB	current
16k	502.5	26.5	15.2 GB	view
32k	453.3	10.3	16.0 GB	view
64k	360.7	6.4	17.7 GB	view
128k	223.5	4.2	21.2 GB	view
195k	183.4	2.6	25.0 GB	view