← Back to community benchmarks

gemma-4-E4B-it-oQ4

M1 Max (24c) · 64 GB · 4bit · 2026-05-18

Performance

1k

tokens

1,118

PP tok/s

64.6

TG tok/s

916

TTFT (ms)

5.1

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.9.dev2

macOS macOS 15.7.7

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,118	64.6	5.1 GB	current
4k	1,120	60.8	5.3 GB	view
8k	1,103	57.0	5.4 GB	view
16k	1,070	51.7	5.6 GB	view
32k	998.7	42.0	6.3 GB	view
64k	874.2	3.5	8.6 GB	view