← Back to community benchmarks

gemma-4-E2B-it-ultra-uncensored-heretic4bit-mixed_4_6

M4 (10c) · 16 GB · 4bit · 2026-06-09

Performance

32k

tokens

1,648

PP tok/s

41.6

TG tok/s

19887

TTFT (ms)

4.2

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.4.2

macOS macOS 26.5.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,457	58.7	3.7 GB	view
4k	1,972	50.5	3.7 GB	view
32k	1,648	41.6	4.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	58.7	1.00×
2×	103.9	1.77×
4×	126.1	2.15×