← Back to community benchmarks

gemma-4-E2B-it-mxfp4

M3 Pro (14c) · 36 GB · 4bit · 2026-04-17

Performance

4k

tokens

2,400

PP tok/s

73.9

TG tok/s

1706

TTFT (ms)

3.0

Peak mem (GB)

Hardware

Chip M3 Pro (14c)

Memory 36 GB

GPU Cores 14

Software

oMLX v0.3.5.dev1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,646	77.4	2.9 GB	view
4k	2,400	73.9	3.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	77.4	1.00×
2×	147.1	1.90×
4×	191.7	2.48×