← Back to community benchmarks

gemma-4-26b-a4b-it

M4 (10c) · 32 GB · 4bit · 2026-04-15

Performance

64k

tokens

200.0

PP tok/s

2.9

TG tok/s

327689

TTFT (ms)

20.1

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.5.dev2

macOS macOS 26.2

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	372.0	32.2	17.1 GB	view
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	current