Model comparison

Qwen3.6-27B vs c4ai-command-r-plus-08-2024

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 62,750,608,128. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 4.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-27Bc4ai-command-r-plus-08-2024
Parameters27.8B104B
Architectureqwen35command-r
Layers6464
Native context262,144131,072
Mixture of expertsnono
Quantizations published4045
Smallest quantization8.74 GiB21.59 GiB
Q4_K_M15.41 GiB58.44 GiB
Licenceapache-2.0cc-by-nc-4.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-27Bc4ai-command-r-plus-08-2024Ratio
4,0960.25 GiB1.00 GiB4.00×
8,1920.50 GiB2.00 GiB4.00×
16,3841.00 GiB4.00 GiB4.00×
32,7682.00 GiB8.00 GiB4.00×
65,5364.00 GiB16.00 GiB4.00×
131,0728.00 GiB32.00 GiB4.00×