Is Qwen3-VL-32B-Thinking or gemma-4-12B-it 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

Qwen3-VL-32B-Thinking vs gemma-4-12B-it

At Q4_K_M, gemma-4-12B-it is the smaller download — 7,121,861,440 bytes against 19,762,150,240. 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

	Qwen3-VL-32B-Thinking	gemma-4-12B-it
Parameters	33.4B	12.0B
Architecture	qwen3vl	gemma4
Layers	64	48
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	25	59
Smallest quantization	7.21 GiB	3.92 GiB
Q4_K_M	18.40 GiB	6.63 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-VL-32B-Thinking	gemma-4-12B-it	Ratio
4,096	1.00 GiB	0.72 GiB	1.39×
8,192	2.00 GiB	0.97 GiB	2.06×
16,384	4.00 GiB	1.47 GiB	2.72×
32,768	8.00 GiB	2.47 GiB	3.24×
65,536	16.00 GiB	4.47 GiB	3.58×
131,072	32.00 GiB	8.47 GiB	3.78×