← Back to community benchmarks

gemma-4-E4B-it

M2 (10c) · 24 GB · 8bit · 2026-04-18

Performance

1k

tokens

284.3

PP tok/s

14.8

TG tok/s

3601

TTFT (ms)

7.9

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.6

macOS macOS 26.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	284.3	14.8	7.9 GB	current
4k	310.2	15.8	8.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	14.8	1.00×
2×	30.7	2.07×
4×	46.9	3.17×