← Back to community benchmarks

gemma-4-E4B-it

M1 Ultra (48c) · 64 GB · 8bit · 2026-04-15

Performance

1k

tokens

927.6

PP tok/s

62.3

TG tok/s

1104

TTFT (ms)

8.1

Peak mem (GB)

Hardware

Chip M1 Ultra (48c)

Memory 64 GB

GPU Cores 48

Software

oMLX v0.3.5

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	927.6	62.3	8.1 GB	current
4k	1,180	59.2	8.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	62.3	1.00×
2×	100.7	1.62×
4×	140.5	2.26×