Model comparison

North-Mini-Code-1.0 vs Qwen3.8-27B

At Q4_K_M, Qwen3.8-27B is the smaller download — 16,810,714,336 bytes against 18,744,024,640. At long context the gap widens: North-Mini-Code-1.0's KV cache at 32K is 1.8× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

North-Mini-Code-1.0Qwen3.8-27B
Parameters30.5B27.8B
Architecturecohere2moeqwen35
Layers4964
Native context500,000262,144
Mixture of expertsyes, 128 expertsno
Quantizations published4122
Smallest quantization7.93 GiB8.39 GiB
Q4_K_M17.46 GiB15.66 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextNorth-Mini-Code-1.0Qwen3.8-27BRatio
4,0960.38 GiB0.25 GiB1.53×
8,1920.52 GiB0.50 GiB1.04×
16,3840.72 GiB1.00 GiB1.38×
32,7681.13 GiB2.00 GiB1.77×
65,5361.94 GiB4.00 GiB2.06×
131,0723.57 GiB8.00 GiB2.24×