← Back to community benchmarks

gemma-4-E4B-it

M3 Pro (18c) · 36 GB · unknown · 2026-04-23

Performance

4k

tokens

1,025

PP tok/s

12.9

TG tok/s

3996

TTFT (ms)

15.4

Peak mem (GB)

Hardware

Chip M3 Pro (18c)

Memory 36 GB

GPU Cores 18

Software

oMLX v0.3.7

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	925.0	12.8	15.3 GB	view
4k	1,025	12.9	15.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	12.8	1.00×
2×	17.5	1.37×
4×	33.9	2.65×