← Back to community benchmarks

North-Mini-Code-1.0-5bit

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

Performance

4k

tokens

1,175

PP tok/s

70.6

TG tok/s

3486

TTFT (ms)

21.9

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.4.3

macOS macOS 26.6

Context 4,096

Performance by Context Length

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

Batching Results

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