Model comparison

Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 vs Qwen3.8-27B

At Q4_K_M, Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 is the smaller download — 16,547,399,712 bytes against 16,810,714,336.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16Qwen3.8-27B
Parameters27.4B27.8B
Architectureqwen35qwen35
Layers6464
Native context262,144262,144
Mixture of expertsnono
Quantizations published2922
Smallest quantization9.98 GiB8.39 GiB
Q4_K_M15.41 GiB15.66 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-27B-AEON-Ultimate-Uncensored-BF16Qwen3.8-27BRatio
4,0960.25 GiB0.25 GiB1.00×
8,1920.50 GiB0.50 GiB1.00×
16,3841.00 GiB1.00 GiB1.00×
32,7682.00 GiB2.00 GiB1.00×
65,5364.00 GiB4.00 GiB1.00×
131,0728.00 GiB8.00 GiB1.00×