Is gemma-3-12b-it-ultra-uncensored-heretic or Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP smaller?

gemma-3-12b-it-ultra-uncensored-heretic is smaller at Q4_K_M: 6.80 GiB against 34.04 GiB.

Which uses less memory at long context?

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

gemma-3-12b-it-ultra-uncensored-heretic vs Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP

At Q4_K_M, gemma-3-12b-it-ultra-uncensored-heretic is the smaller download — 7,300,780,096 bytes against 36,545,830,912. At long context the gap widens: Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP's KV cache at 32K is 1.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-3-12b-it-ultra-uncensored-heretic	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
Parameters	12.2B	27.8B
Architecture	gemma3	qwen35
Layers	48	64
Native context	131,072	262,144
Mixture of experts	no	no
Quantizations published	21	34
Smallest quantization	4.44 GiB	10.12 GiB
Q4_K_M	6.80 GiB	34.04 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-3-12b-it-ultra-uncensored-heretic	Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP	Ratio
4,096	0.72 GiB	0.25 GiB	2.87×
8,192	0.97 GiB	0.50 GiB	1.94×
16,384	1.47 GiB	1.00 GiB	1.47×
32,768	2.47 GiB	2.00 GiB	1.23×
65,536	4.47 GiB	4.00 GiB	1.12×
131,072	8.47 GiB	8.00 GiB	1.06×