← Back to community benchmarks

gemma-4-e4b-it

M3 Pro (14c) · 18 GB · 4bit · 2026-04-30

Performance

1k

tokens

737.1

PP tok/s

41.0

TG tok/s

1389

TTFT (ms)

5.6

Peak mem (GB)

Hardware

Chip M3 Pro (14c)

Memory 18 GB

GPU Cores 14

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	737.1	41.0	5.6 GB	current
4k	775.3	39.5	5.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	41.0	1.00×
2×	78.5	1.91×
4×	97.3	2.37×