Is Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness or gemma-4-26B-A4B-it smaller?

Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness is smaller at Q4_K_M: 5.09 GiB against 15.64 GiB.

Which uses less memory at long context?

Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness — its KV cache at 32K context is 3.1x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness vs gemma-4-26B-A4B-it

At Q4_K_M, Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness is the smaller download — 5,463,652,192 bytes against 16,796,017,248. At long context the gap widens: Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness's KV cache at 32K is 3.1× 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	gemma-4-26B-A4B-it
Parameters	9.1B	26.5B
Architecture	qwen35	gemma4
Layers	16	30
Native context	262,144	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	2	46
Smallest quantization	4.88 GiB	8.99 GiB
Q4_K_M	5.09 GiB	15.64 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	gemma-4-26B-A4B-it	Ratio
4,096	0.06 GiB	0.45 GiB	7.18×
8,192	0.13 GiB	0.61 GiB	4.84×
16,384	0.25 GiB	0.92 GiB	3.67×
32,768	0.50 GiB	1.54 GiB	3.09×
65,536	1.00 GiB	2.79 GiB	2.79×
131,072	2.00 GiB	5.29 GiB	2.65×