← Back to community benchmarks

gemma-4-E2B-it-oQ6

M1 Max (24c) · 32 GB · 6bit · 2026-05-07

Performance

32k

tokens

3,032

PP tok/s

62.9

TG tok/s

10806

TTFT (ms)

7.7

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	2,025	81.1	7.2 GB	view
4k	3,552	79.8	7.3 GB	view
8k	3,737	76.3	7.3 GB	view
16k	3,479	70.3	7.4 GB	view
32k	3,032	62.9	7.7 GB	current
64k	2,371	51.2	8.4 GB	view
128k	1,620	35.9	9.9 GB	view