← Back to community benchmarks

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

M4 Max (40c) · 128 GB · 8bit · 2026-06-03

Performance

1k

tokens

1,164

PP tok/s

78.9

TG tok/s

880

TTFT (ms)

25.8

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 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,164	78.9	25.8 GB	current
4k	1,389	76.4	26.3 GB	view
8k	1,403	74.3	26.7 GB	view
16k	1,350	69.7	27.1 GB	view
32k	1,227	62.1	28.0 GB	view
64k	1,019	51.0	30.0 GB	view