← Back to community benchmarks

gemma-4-e4b

M4 (10c) · 16 GB · 8bit · 2026-04-12

Performance

1k

tokens

398.0

PP tok/s

19.0

TG tok/s

2575

TTFT (ms)

7.9

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.3.5.dev1

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	398.0	19.0	7.9 GB	current
4k	443.1	17.4	8.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	19.0	1.00×
2×	35.3	1.86×
4×	48.0	2.53×