Model comparison

Phi-3.5-MoE-instruct vs Qwen3.6-27B

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 25,345,994,304.

From the file· summed bytes, KV per layer

Side by side

Phi-3.5-MoE-instructQwen3.6-27B
Parameters41.9B27.8B
Architecturephimoeqwen35
Layers3264
Native context131,072262,144
Mixture of expertsyes, 16 expertsno
Quantizations published2940
Smallest quantization10.27 GiB8.74 GiB
Q4_K_M23.61 GiB15.41 GiB
Licencemitapache-2.0

KV cache by context

the term that decides long-context viability
ContextPhi-3.5-MoE-instructQwen3.6-27BRatio
4,0960.25 GiB
8,1920.50 GiB
16,3841.00 GiB
32,7682.00 GiB
65,5364.00 GiB
131,0728.00 GiB