← Back to community benchmarks

North-Mini-Code-1.0

M3 Ultra (60c) · 256 GB · 4bit · 2026-07-01

Performance

4k

tokens

1,825

PP tok/s

74.2

TG tok/s

2245

TTFT (ms)

18.5

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.4.4

macOS macOS 26.5.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,644	80.7	17.9 GB	view
4k	1,825	74.2	18.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	80.7	1.00×
2×	90.9	1.13×
4×	150.2	1.86×