← Back to community benchmarks

gemma-4-e4b-it

M1 Pro (14c) · 16 GB · 8bit · 2026-04-17

Performance

1k

tokens

326.4

PP tok/s

23.3

TG tok/s

3138

TTFT (ms)

8.0

Peak mem (GB)

Hardware

Chip M1 Pro (14c)

Memory 16 GB

GPU Cores 14

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	326.4	23.3	8.0 GB	current
4k	382.9	22.6	8.1 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	23.3	1.00×
2×	46.3	1.99×
4×	54.2	2.33×