Is gemma-4-12B-it or Qwen3.5-35B-A3B-ultra-uncensored-heretic smaller?

gemma-4-12B-it is smaller at Q4_K_M: 6.63 GiB against 19.72 GiB.

Which uses less memory at long context?

Qwen3.5-35B-A3B-ultra-uncensored-heretic — its KV cache at 32K context is 3.9x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it vs Qwen3.5-35B-A3B-ultra-uncensored-heretic

At Q4_K_M, gemma-4-12B-it is the smaller download — 7,121,861,440 bytes against 21,169,117,024. At long context the gap widens: Qwen3.5-35B-A3B-ultra-uncensored-heretic's KV cache at 32K is 3.9× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-4-12B-it	Qwen3.5-35B-A3B-ultra-uncensored-heretic
Parameters	12.0B	35.1B
Architecture	gemma4	qwen35moe
Layers	48	40
Native context	262,144	262,144
Mixture of experts	no	yes, 256 experts
Quantizations published	59	8
Smallest quantization	3.92 GiB	8.70 GiB
Q4_K_M	6.63 GiB	19.72 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-12B-it	Qwen3.5-35B-A3B-ultra-uncensored-heretic	Ratio
4,096	0.72 GiB	0.08 GiB	9.19×
8,192	0.97 GiB	0.16 GiB	6.20×
16,384	1.47 GiB	0.31 GiB	4.70×
32,768	2.47 GiB	0.63 GiB	3.95×
65,536	4.47 GiB	1.25 GiB	3.57×
131,072	8.47 GiB	2.50 GiB	3.39×