← Back to community benchmarks

gemma-4-e4b-it-oQ5

M1 Max (32c) · 64 GB · 5bit · 2026-07-13

Performance

4k

tokens

1,124

PP tok/s

54.5

TG tok/s

3646

TTFT (ms)

5.7

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	1,124	54.5	5.7 GB	current
16k	779.7	42.8	6.0 GB	view
64k	641.4	25.1	7.3 GB	view