Model comparison

chatglm3-6b vs Qwen3.6-27B

At Q4_K_M, chatglm3-6b is the smaller download — 4,140,342,688 bytes against 16,547,397,888.

From the file· summed bytes, KV per layer

Side by side

chatglm3-6bQwen3.6-27B
Parameters6.2B27.8B
Architecturechatglmqwen35
Layers64
Native context262,144
Mixture of expertsnono
Quantizations published340
Smallest quantization3.86 GiB8.74 GiB
Q4_K_M3.86 GiB15.41 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
Contextchatglm3-6bQwen3.6-27BRatio
4,0960.25 GiB
8,1920.50 GiB
16,3841.00 GiB
32,7682.00 GiB
65,5364.00 GiB
131,0728.00 GiB