← Back to community benchmarks

gemma-4-e4b-it

M1 Max (32c) · 64 GB · 4bit · 2026-05-25

Performance

16k

tokens

845.0

PP tok/s

47.8

TG tok/s

19390

TTFT (ms)

6.0

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.10

macOS macOS 26.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	759.9	63.3	5.6 GB	view
4k	844.7	59.0	5.7 GB	view
8k	866.4	54.1	5.8 GB	view
16k	845.0	47.8	6.0 GB	current
32k	801.8	37.3	6.7 GB	view
64k	723.2	23.5	7.6 GB	view
128k	592.3	14.8	9.9 GB	view