← Back to community benchmarks

gemma-4-e2b-it

M3 Pro (14c) · 36 GB · 4bit · 2026-04-16

Performance

1k

tokens

1,191

PP tok/s

64.6

TG tok/s

860

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 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,191	64.6	3.0 GB	current
4k	2,062	62.4	3.1 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	64.6	1.00×
2×	125.0	1.93×
4×	161.0	2.49×