← Back to community benchmarks

gemma-4-26B-A4B-it5bit

M1 Pro (14c) · 32 GB · 5bit · 2026-05-18

Performance

16k

tokens

191.1

PP tok/s

19.9

TG tok/s

85721

TTFT (ms)

18.1

Peak mem (GB)

Hardware

Chip M1 Pro (14c)

Memory 32 GB

GPU Cores 14

Software

oMLX v0.3.9.dev2

macOS macOS 26.3.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	191.1	19.9	18.1 GB	current
32k	194.7	16.8	19.4 GB	view
64k	165.8	12.5	21.4 GB	view