← Back to community benchmarks

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

M4 Pro (16c) · 48 GB · 6bit · 2026-05-16

Performance

16k

tokens

560.5

PP tok/s

43.4

TG tok/s

29233

TTFT (ms)

21.5

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.8

macOS macOS 15.7.7

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	588.9	46.9	20.8 GB	view
16k	560.5	43.4	21.5 GB	current
32k	499.4	37.6	22.5 GB	view
64k	403.2	28.5	24.5 GB	view