← Back to community benchmarks

gemma-4-e2b-it

M1 Max (24c) · 64 GB · 4bit · 2026-04-03

Performance

1k

tokens

1,373

PP tok/s

60.3

TG tok/s

746

TTFT (ms)

3.9

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.1

macOS macOS 15.7.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,373	60.3	3.9 GB	current
4k	2,143	58.5	3.9 GB	view
8k	2,289	54.8	4.0 GB	view
16k	2,138	48.8	4.1 GB	view
32k	1,899	42.7	4.4 GB	view
64k	1,464	29.5	5.1 GB	view
128k	1,016	17.6	6.6 GB	view