← Back to community benchmarks

gemma-4-e4b-it

M5 Pro (20c) · 64 GB · 6bit · 2026-04-17

Performance

1k

tokens

1,848

PP tok/s

58.5

TG tok/s

554

TTFT (ms)

10.3

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,848	58.5	10.3 GB	current
4k	2,887	51.4	10.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	58.5	1.00×
2×	98.1	1.68×
4×	117.6	2.01×