← Back to community benchmarks

North-Mini-Code-1.0-oQ6

M3 Ultra (80c) · 256 GB · 6bit · 2026-06-12

Performance

8k

tokens

2,016

PP tok/s

103.6

TG tok/s

4063

TTFT (ms)

24.7

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 256 GB

GPU Cores 80

Software

oMLX v0.4.4rc1

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	2,016	103.6	24.7 GB	current
16k	1,821	98.1	25.6 GB	view
32k	1,583	90.7	26.0 GB	view
64k	1,265	76.4	27.3 GB	view
128k	912.4	58.8	29.8 GB	view