← Back to community benchmarks

gemma-4-e4b-it

M5 Pro (20c) · 48 GB · 4bit · 2026-04-14

Performance

4k

tokens

3,509

PP tok/s

76.8

TG tok/s

1167

TTFT (ms)

4.7

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,178	81.5	4.6 GB	view
4k	3,509	76.8	4.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	81.5	1.00×
2×	147.8	1.81×
4×	204.9	2.51×