Is Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness or Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness — its KV cache at 32K context is 4.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness vs Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness'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

	Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
Parameters	9.1B	27.8B
Architecture	qwen35	qwen35
Layers	16	64
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	2	34
Smallest quantization	16.09 GiB	10.12 GiB
Q4_K_M	—	34.04 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP	Ratio
4,096	0.06 GiB	0.25 GiB	4.00×
8,192	0.13 GiB	0.50 GiB	4.00×
16,384	0.25 GiB	1.00 GiB	4.00×
32,768	0.50 GiB	2.00 GiB	4.00×
65,536	1.00 GiB	4.00 GiB	4.00×
131,072	2.00 GiB	8.00 GiB	4.00×