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

Qwen3.5-2B is smaller at Q4_K_M: 1.18 GiB against 1.44 GiB.

Which uses less memory at long context?

Qwen3.5-2B — its KV cache at 32K context is 6.7x smaller, because of how its attention layers cache.

Model comparison

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

At Q4_K_M, Qwen3.5-2B is the smaller download — 1,270,808,032 bytes against 1,545,294,400. At long context the gap widens: Qwen3.5-2B's KV cache at 32K is 6.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	granite-vision-3.2-2b	Qwen3.5-2B
Parameters	3.0B	2.3B
Architecture	granite	qwen35
Layers	40	24
Native context	131,072	262,144
Mixture of experts	no	no
Quantizations published	30	42
Smallest quantization	0.83 GiB	0.72 GiB
Q4_K_M	1.44 GiB	1.18 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	granite-vision-3.2-2b	Qwen3.5-2B	Ratio
4,096	0.31 GiB	0.05 GiB	6.66×
8,192	0.63 GiB	0.09 GiB	6.66×
16,384	1.25 GiB	0.19 GiB	6.67×
32,768	2.50 GiB	0.38 GiB	6.67×
65,536	5.00 GiB	0.75 GiB	6.67×
131,072	10.00 GiB	1.50 GiB	6.67×