Model comparison

Qwen3.6-27B vs pig-1k

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 40,239,547,872.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-27Bpig-1k
Parameters27.8B6.9B
Architectureqwen35pig
Layers64
Native context262,144
Mixture of expertsnono
Quantizations published4011
Smallest quantization8.74 GiB6.10 GiB
Q4_K_M15.41 GiB37.48 GiB
Licenceapache-2.0mit

KV cache by context

the term that decides long-context viability
ContextQwen3.6-27Bpig-1kRatio
4,0960.25 GiB
8,1920.50 GiB
16,3841.00 GiB
32,7682.00 GiB
65,5364.00 GiB
131,0728.00 GiB