← Back to community benchmarks

gemma-4-26b-a4b-it

M4 (10c) · 32 GB · 4bit · 2026-04-15

Performance

4k

tokens

372.0

PP tok/s

32.2

TG tok/s

11010

TTFT (ms)

17.1

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.5.dev2

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	372.0	32.2	17.1 GB	current
16k	289.5	22.0	17.6 GB	view
32k	257.0	11.8	18.4 GB	view
64k	200.0	2.9	20.1 GB	view