← Back to community benchmarks

gemma-4-e4b-it

M5 (10c) · 24 GB · 4bit · 2026-05-20

Performance

1k

tokens

1,304

PP tok/s

27.3

TG tok/s

786

TTFT (ms)

5.9

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.6

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,304	27.3	5.9 GB	current
4k	1,706	26.3	5.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.3	1.00×
2×	54.2	1.99×
4×	83.4	3.05×