← Back to community benchmarks

gemma-4-26B-A4B-it-oQ6

M5 Max (40c) · 128 GB · 6bit · 2026-05-19

Performance

16k

tokens

3,434

PP tok/s

78.4

TG tok/s

4772

TTFT (ms)

22.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9rc1

macOS macOS 26.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,169	92.7	20.7 GB	view
4k	3,206	89.6	21.3 GB	view
8k	3,451	85.5	21.6 GB	view
16k	3,434	78.4	22.0 GB	current
32k	3,016	70.0	22.9 GB	view
64k	2,465	56.8	24.9 GB	view