Is Qwen3.6-35B-A3B-uncensored-heretic or Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP smaller?

Qwen3.6-35B-A3B-uncensored-heretic is smaller at Q4_K_M: 19.78 GiB against 34.04 GiB.

Which uses less memory at long context?

Qwen3.6-35B-A3B-uncensored-heretic — its KV cache at 32K context is 3.2x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-35B-A3B-uncensored-heretic vs Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP

At Q4_K_M, Qwen3.6-35B-A3B-uncensored-heretic is the smaller download — 21,233,608,512 bytes against 36,545,830,912. At long context the gap widens: Qwen3.6-35B-A3B-uncensored-heretic's KV cache at 32K is 3.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-35B-A3B-uncensored-heretic	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
Parameters	35.1B	27.8B
Architecture	qwen35moe	qwen35
Layers	40	64
Native context	262,144	262,144
Mixture of experts	yes, 256 experts	no
Quantizations published	10	34
Smallest quantization	15.71 GiB	10.12 GiB
Q4_K_M	19.78 GiB	34.04 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-35B-A3B-uncensored-heretic	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP	Ratio
4,096	0.08 GiB	0.25 GiB	3.20×
8,192	0.16 GiB	0.50 GiB	3.20×
16,384	0.31 GiB	1.00 GiB	3.20×
32,768	0.63 GiB	2.00 GiB	3.20×
65,536	1.25 GiB	4.00 GiB	3.20×
131,072	2.50 GiB	8.00 GiB	3.20×