Model comparison

c4ai-command-r-08-2024 vs Qwen3.8-27B

At Q4_K_M, Qwen3.8-27B is the smaller download — 16,810,714,336 bytes against 19,800,833,184. At long context the gap widens: Qwen3.8-27B's KV cache at 32K is 2.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

c4ai-command-r-08-2024Qwen3.8-27B
Parameters32.3B27.8B
Architecturecommand-rqwen35
Layers4064
Native context131,072262,144
Mixture of expertsnono
Quantizations published2822
Smallest quantization9.61 GiB8.39 GiB
Q4_K_M18.44 GiB15.66 GiB
Licencecc-by-nc-4.0apache-2.0

KV cache by context

the term that decides long-context viability
Contextc4ai-command-r-08-2024Qwen3.8-27BRatio
4,0960.63 GiB0.25 GiB2.50×
8,1921.25 GiB0.50 GiB2.50×
16,3842.50 GiB1.00 GiB2.50×
32,7685.00 GiB2.00 GiB2.50×
65,53610.00 GiB4.00 GiB2.50×
131,07220.00 GiB8.00 GiB2.50×