← Back to community benchmarks

North-Mini-Code-1.0

M4 Max (40c) · 64 GB · 6bit · 2026-07-01
Performance
32k
tokens
932.8
PP tok/s
69.0
TG tok/s
35131
TTFT (ms)
26.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.4
macOS macOS 26.5.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,388 94.5 24.9 GB view
4k 1,429 84.1 25.4 GB view
8k 1,244 81.2 25.6 GB view
16k 1,096 77.2 26.0 GB view
32k 932.8 69.0 26.4 GB current
Batching Results
Batch Size TG tok/s Speedup
94.5 1.00×
83.9 0.89×
124.3 1.32×