Is gemma-4-12B-it or Qwen3-VL-32B-Instruct-ultra-uncensored-heretic smaller?

gemma-4-12B-it is smaller at Q4_K_M: 6.63 GiB against 18.40 GiB.

Which uses less memory at long context?

gemma-4-12B-it — its KV cache at 32K context is 3.2x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it vs Qwen3-VL-32B-Instruct-ultra-uncensored-heretic

At Q4_K_M, gemma-4-12B-it is the smaller download — 7,121,861,440 bytes against 19,762,151,392. At long context the gap widens: gemma-4-12B-it's KV cache at 32K is 3.2× 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-VL-32B-Instruct-ultra-uncensored-heretic
Parameters	12.0B	33.4B
Architecture	gemma4	qwen3vl
Layers	48	64
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	59	43
Smallest quantization	3.92 GiB	6.82 GiB
Q4_K_M	6.63 GiB	18.40 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-VL-32B-Instruct-ultra-uncensored-heretic	Ratio
4,096	0.72 GiB	1.00 GiB	1.39×
8,192	0.97 GiB	2.00 GiB	2.06×
16,384	1.47 GiB	4.00 GiB	2.72×
32,768	2.47 GiB	8.00 GiB	3.24×
65,536	4.47 GiB	16.00 GiB	3.58×
131,072	8.47 GiB	32.00 GiB	3.78×