← Back to community benchmarks

gemma-4-E4B-it

M4 Pro (20c) · 24 GB · 4bit · 2026-06-05

Performance

64k

tokens

908.8

PP tok/s

12.2

TG tok/s

72111

TTFT (ms)

9.4

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 24 GB

GPU Cores 20

Software

oMLX v0.4.2.dev2

macOS macOS 15.7.3

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,060	45.6	7.0 GB	view
4k	1,191	45.0	7.1 GB	view
8k	1,200	42.9	7.3 GB	view
16k	1,164	40.3	7.5 GB	view
32k	1,067	33.7	8.2 GB	view
64k	908.8	12.2	9.4 GB	current