← Back to community benchmarks

gemma-4-26B-A4B-it-oQ8

M4 Max (40c) · 128 GB · 8bit · 2026-06-05

Performance

64k

tokens

1,017

PP tok/s

50.0

TG tok/s

64475

TTFT (ms)

30.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 15.7.4

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,185	77.0	25.8 GB	view
4k	1,394	74.5	26.3 GB	view
8k	1,404	72.4	26.8 GB	view
16k	1,347	68.1	27.1 GB	view
32k	1,224	60.4	28.0 GB	view
64k	1,017	50.0	30.0 GB	current