← Back to community benchmarks

gemma-4-26B-A4B-it5bit

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

Performance

64k

tokens

165.8

PP tok/s

12.5

TG tok/s

395368

TTFT (ms)

21.4

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 65,536

Performance by Context Length

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