← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-04

Performance

1k

tokens

1,690

PP tok/s

85.4

TG tok/s

606

TTFT (ms)

25.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,690	85.4	25.8 GB	current
4k	2,213	82.7	26.4 GB	view
8k	2,745	80.2	26.6 GB	view
16k	2,814	74.4	27.1 GB	view
32k	2,615	64.8	27.5 GB	view
64k	2,120	49.5	29.2 GB	view
128k	1,444	33.5	32.7 GB	view