← Back to community benchmarks

gemma-4-e2b-it

M1 Pro (16c) · 16 GB · 4bit · 2026-04-17

Performance

4k

tokens

1,466

PP tok/s

68.2

TG tok/s

2794

TTFT (ms)

3.1

Peak mem (GB)

Hardware

Chip M1 Pro (16c)

Memory 16 GB

GPU Cores 16

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	884.6	70.6	3.0 GB	view
4k	1,466	68.2	3.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	70.6	1.00×
2×	92.2	1.31×
4×	104.8	1.48×