← Back to community benchmarks

gemma-4-E2B-it

M4 Pro (16c) · 48 GB · 4bit · 2026-07-13

Performance

16k

tokens

3,105

PP tok/s

71.4

TG tok/s

5277

TTFT (ms)

4.0

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	3,105	71.4	4.0 GB	current
32k	2,720	59.2	4.3 GB	view
64k	2,115	48.4	5.2 GB	view
128k	1,465	34.7	6.8 GB	view
195k	962.7	11.2	8.9 GB	view