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

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

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

	gemma-4-26B-A4B-it	Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness
Parameters	26.5B	9.1B
Architecture	gemma4	qwen35
Layers	30	16
Native context	262,144	262,144
Mixture of experts	yes, 128 experts	no
Quantizations published	46	2
Smallest quantization	8.99 GiB	4.88 GiB
Q4_K_M	15.64 GiB	5.09 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-26B-A4B-it	Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness	Ratio
4,096	0.45 GiB	0.06 GiB	7.18×
8,192	0.61 GiB	0.13 GiB	4.84×
16,384	0.92 GiB	0.25 GiB	3.67×
32,768	1.54 GiB	0.50 GiB	3.09×
65,536	2.79 GiB	1.00 GiB	2.79×
131,072	5.29 GiB	2.00 GiB	2.65×