← Back to community benchmarks

North-Mini-Code-1.0

M2 Max (30c) · 32 GB · 4bit · 2026-06-10
Performance
4k
tokens
504.3
PP tok/s
53.5
TG tok/s
8124
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 32 GB
GPU Cores 30
Software
oMLX v0.4.3
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 539.4 63.0 17.9 GB view
4k 504.3 53.5 18.2 GB current
16k 402.2 45.7 18.8 GB view
Batching Results
Batch Size TG tok/s Speedup
63.0 1.00×
119.9 1.90×
251.2 3.99×
503.5 7.99×