Model comparison

Qwen3.6-35B-A3B vs glm-4v-9b

At Q4_K_M, glm-4v-9b is the smaller download — 6,166,574,560 bytes against 21,166,757,728.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-35B-A3Bglm-4v-9b
Parameters36.0B13.9B
Architectureqwen35moeglm4
Layers40
Native context262,144
Mixture of expertsyes, 256 expertsno
Quantizations published6114
Smallest quantization8.77 GiB3.73 GiB
Q4_K_M19.71 GiB5.74 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-35B-A3Bglm-4v-9bRatio
4,0960.08 GiB
8,1920.16 GiB
16,3840.31 GiB
32,7680.63 GiB
65,5361.25 GiB
131,0722.50 GiB