← Back to community benchmarks

Nanbeige4.1-3B-heretic

M4 (10c) · 24 GB · unknown · 2026-03-10

Performance

4k

tokens

414.8

PP tok/s

5.8

TG tok/s

9876

TTFT (ms)

8.1

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.2.7

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	252.6	2.6	7.7 GB	view
4k	414.8	5.8	8.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	2.6	1.00×
2×	12.4	4.77×
4×	7.2	2.77×