← Back to community benchmarks

North-Mini-Code-1.0-5bit

M3 Max (40c) · 48 GB · 5bit · 2026-06-10

Performance

1k

tokens

1,214

PP tok/s

77.2

TG tok/s

845

TTFT (ms)

21.4

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.4.3

macOS macOS 26.6

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,214	77.2	21.4 GB	current
4k	1,175	70.6	21.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	77.2	1.00×
2×	74.2	0.96×
4×	108.3	1.40×