Is Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop or Qwen3.8-27B smaller?

Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop is smaller at Q4_K_M: 6.82 GiB against 15.66 GiB.

Which uses less memory at long context?

Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop — its KV cache at 32K context is 2.7x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop vs Qwen3.8-27B

At Q4_K_M, Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop is the smaller download — 7,323,108,608 bytes against 16,810,714,336. 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-Hightop	Qwen3.8-27B
Parameters	12.1B	27.8B
Architecture	qwen35	qwen35
Layers	24	64
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	33	22
Smallest quantization	4.60 GiB	8.39 GiB
Q4_K_M	6.82 GiB	15.66 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-12B-IQ-Ultra-Heretic-Uncensored-Thinking-V2-Hightop	Qwen3.8-27B	Ratio
4,096	0.09 GiB	0.25 GiB	2.67×
8,192	0.19 GiB	0.50 GiB	2.67×
16,384	0.38 GiB	1.00 GiB	2.67×
32,768	0.75 GiB	2.00 GiB	2.67×
65,536	1.50 GiB	4.00 GiB	2.67×
131,072	3.00 GiB	8.00 GiB	2.67×