Is Qwen3.5-4B or granite-vision-3.2-2b smaller?

granite-vision-3.2-2b is smaller at Q4_K_M: 1.44 GiB against 2.52 GiB.

Which uses less memory at long context?

Qwen3.5-4B — its KV cache at 32K context is 2.5x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-4B vs granite-vision-3.2-2b

At Q4_K_M, granite-vision-3.2-2b is the smaller download — 1,545,294,400 bytes against 2,707,513,696. At long context the gap widens: Qwen3.5-4B's KV cache at 32K is 2.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-4B	granite-vision-3.2-2b
Parameters	4.7B	3.0B
Architecture	qwen35	granite
Layers	32	40
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	57	30
Smallest quantization	1.42 GiB	0.83 GiB
Q4_K_M	2.52 GiB	1.44 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-4B	granite-vision-3.2-2b	Ratio
4,096	0.13 GiB	0.31 GiB	2.50×
8,192	0.25 GiB	0.63 GiB	2.50×
16,384	0.50 GiB	1.25 GiB	2.50×
32,768	1.00 GiB	2.50 GiB	2.50×
65,536	2.00 GiB	5.00 GiB	2.50×
131,072	4.00 GiB	10.00 GiB	2.50×