← Back to community benchmarks

gemma-4-e2b-it

M1 Pro (14c) · 16 GB · 4bit · 2026-05-18

Performance

1k

tokens

781.5

PP tok/s

30.9

TG tok/s

1310

TTFT (ms)

4.0

Peak mem (GB)

Hardware

Chip M1 Pro (14c)

Memory 16 GB

GPU Cores 14

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	781.5	30.9	4.0 GB	current
4k	662.4	34.3	4.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	30.9	1.00×
2×	42.7	1.38×
4×	74.0	2.39×