Model comparison

Qwen3.6-35B-A3B vs InternVL3_5-14B

At Q4_K_M, InternVL3_5-14B is the smaller download — 9,001,749,952 bytes against 21,166,757,728.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-35B-A3BInternVL3_5-14B
Parameters36.0B15.1B
Architectureqwen35moeqwen3
Layers40
Native context262,144
Mixture of expertsyes, 256 expertsno
Quantizations published6128
Smallest quantization8.77 GiB4.62 GiB
Q4_K_M19.71 GiB8.38 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-35B-A3BInternVL3_5-14BRatio
4,0960.08 GiB
8,1920.16 GiB
16,3840.31 GiB
32,7680.63 GiB
65,5361.25 GiB
131,0722.50 GiB