← Back to community benchmarks

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

M4 Max (40c) · 128 GB · 8bit · 2026-05-27

Performance

64k

tokens

1,015

PP tok/s

49.9

TG tok/s

64572

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	1,178	76.5	25.8 GB	view
4k	1,392	74.4	26.3 GB	view
8k	1,403	71.8	26.8 GB	view
16k	1,347	68.0	27.1 GB	view
32k	1,221	60.2	28.0 GB	view
64k	1,015	49.9	30.0 GB	current