Model comparison

Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop vs Qwen3.6-27B

At Q4_K_M, Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop is the smaller download — 7,323,108,608 bytes against 16,547,397,888. At long context the gap widens: Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop's KV cache at 32K is 2.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-HightopQwen3.6-27B
Parameters12.1B27.8B
Architectureqwen35qwen35
Layers2464
Native context262,144262,144
Mixture of expertsnono
Quantizations published3340
Smallest quantization4.60 GiB8.74 GiB
Q4_K_M6.82 GiB15.41 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-HightopQwen3.6-27BRatio
4,0960.09 GiB0.25 GiB2.67×
8,1920.19 GiB0.50 GiB2.67×
16,3840.38 GiB1.00 GiB2.67×
32,7680.75 GiB2.00 GiB2.67×
65,5361.50 GiB4.00 GiB2.67×
131,0723.00 GiB8.00 GiB2.67×