Is Qwen3.6-35B-A3B or Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness 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 1.3x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-35B-A3B vs Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness

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 1.3× 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	Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness
Parameters	36.0B	9.1B
Architecture	qwen35moe	qwen35
Layers	40	16
Native context	262,144	262,144
Mixture of experts	yes, 256 experts	no
Quantizations published	61	2
Smallest quantization	8.77 GiB	16.09 GiB
Q4_K_M	19.71 GiB	—
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-35B-A3B	Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness	Ratio
4,096	0.08 GiB	0.06 GiB	1.25×
8,192	0.16 GiB	0.13 GiB	1.25×
16,384	0.31 GiB	0.25 GiB	1.25×
32,768	0.63 GiB	0.50 GiB	1.25×
65,536	1.25 GiB	1.00 GiB	1.25×
131,072	2.50 GiB	2.00 GiB	1.25×