← Back to community benchmarks

gemma-4-E2B-it-UD

M1 Max (24c) · 32 GB · 4bit · 2026-05-03

Performance

32k

tokens

2,085

PP tok/s

58.5

TG tok/s

15720

TTFT (ms)

5.3

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,452	77.9	4.8 GB	view
4k	2,306	75.7	4.9 GB	view
8k	2,456	71.9	4.9 GB	view
16k	2,321	66.5	5.0 GB	view
32k	2,085	58.5	5.3 GB	current
64k	1,719	46.5	6.0 GB	view
128k	1,260	33.1	7.5 GB	view