← Back to community benchmarks

gemma-4-26B-A4B-it-uncensored-oQ5

M4 Pro (20c) · 64 GB · 5bit · 2026-05-06

Performance

32k

tokens

545.9

PP tok/s

39.8

TG tok/s

60026

TTFT (ms)

19.6

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	653.2	46.0	18.3 GB	view
32k	545.9	39.8	19.6 GB	current
64k	459.8	29.8	20.8 GB	view