← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 8bit · 2026-04-03

Performance

64k

tokens

1,715

PP tok/s

24.2

TG tok/s

38212

TTFT (ms)

30.3

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.1

macOS macOS 26.4

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,958	64.0	26.8 GB	view
4k	3,322	61.3	27.1 GB	view
16k	2,202	47.3	27.8 GB	view
32k	2,038	37.6	28.6 GB	view
64k	1,715	24.2	30.3 GB	current
128k	1,192	12.5	33.9 GB	view