← Back to community benchmarks

gemma-4-E2B-it-UD

M1 Max (24c) · 32 GB · 4bit · 2026-05-07

Performance

16k

tokens

2,314

PP tok/s

66.4

TG tok/s

7079

TTFT (ms)

7.1

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 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,502	78.1	6.9 GB	view
4k	2,493	76.1	7.0 GB	view
8k	2,435	72.2	7.0 GB	view
16k	2,314	66.4	7.1 GB	current
32k	2,079	58.4	7.4 GB	view
64k	1,717	47.0	8.1 GB	view
128k	1,260	32.1	9.6 GB	view