← Back to community benchmarks

gemma-4-E4B-it-oQ4

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

Performance

64k

tokens

1,040

PP tok/s

24.2

TG tok/s

62997

TTFT (ms)

6.8

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	954.1	71.5	4.8 GB	view
4k	1,234	66.6	4.8 GB	view
64k	1,040	24.2	6.8 GB	current