← Back to community benchmarks

gemma-4-e2b-it

M1 Max (32c) · 64 GB · 4bit · 2026-04-26

Performance

64k

tokens

2,009

PP tok/s

47.7

TG tok/s

32619

TTFT (ms)

4.2

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,379	100.1	3.0 GB	view
4k	2,306	95.2	3.0 GB	view
64k	2,009	47.7	4.2 GB	current