← Back to community benchmarks

gemma-4-e4b-it

M5 (8c) · 16 GB · 8bit · 2026-04-14

Performance

1k

tokens

1,007

PP tok/s

25.0

TG tok/s

1017

TTFT (ms)

7.9

Peak mem (GB)

Hardware

Chip M5 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,007	25.0	7.9 GB	current
4k	1,448	23.9	8.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	25.0	1.00×
2×	49.4	1.98×
4×	70.8	2.83×