Is gemma-4-12B-it or Qwen3-VL-8B-Thinking smaller?

Qwen3-VL-8B-Thinking is smaller at Q4_K_M: 4.68 GiB against 6.63 GiB.

Which uses less memory at long context?

gemma-4-12B-it — its KV cache at 32K context is 1.8x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it vs Qwen3-VL-8B-Thinking

At Q4_K_M, Qwen3-VL-8B-Thinking is the smaller download — 5,027,784,704 bytes against 7,121,861,440. At long context the gap widens: gemma-4-12B-it's KV cache at 32K is 1.8× 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-8B-Thinking
Parameters	12.0B	8.8B
Architecture	gemma4	qwen3vl
Layers	48	36
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	59	26
Smallest quantization	3.92 GiB	2.12 GiB
Q4_K_M	6.63 GiB	4.68 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-8B-Thinking	Ratio
4,096	0.72 GiB	0.56 GiB	1.28×
8,192	0.97 GiB	1.13 GiB	1.16×
16,384	1.47 GiB	2.25 GiB	1.53×
32,768	2.47 GiB	4.50 GiB	1.82×
65,536	4.47 GiB	9.00 GiB	2.01×
131,072	8.47 GiB	18.00 GiB	2.13×