← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (20c) · 48 GB · 4bit · 2026-04-03

Performance

64k

tokens

458.1

PP tok/s

11.2

TG tok/s

143058

TTFT (ms)

18.6

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.1

macOS macOS 26.3.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	609.9	38.1	15.6 GB	view
16k	569.7	30.0	16.0 GB	view
32k	559.7	17.1	16.8 GB	view
64k	458.1	11.2	18.6 GB	current
128k	350.2	2.2	22.1 GB	view