Is OpenCaption-2B-VL-SFT-v1.0 or Qwen3.5-2B smaller?

OpenCaption-2B-VL-SFT-v1.0 is smaller at Q4_K_M: 1.03 GiB against 1.18 GiB.

Which uses less memory at long context?

Qwen3.5-2B — its KV cache at 32K context is 9.3x smaller, because of how its attention layers cache.

Model comparison

OpenCaption-2B-VL-SFT-v1.0 vs Qwen3.5-2B

At Q4_K_M, OpenCaption-2B-VL-SFT-v1.0 is the smaller download — 1,107,408,032 bytes against 1,270,808,032. At long context the gap widens: Qwen3.5-2B's KV cache at 32K is 9.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	OpenCaption-2B-VL-SFT-v1.0	Qwen3.5-2B
Parameters	2.1B	2.3B
Architecture	qwen3vl	qwen35
Layers	28	24
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	50	42
Smallest quantization	0.48 GiB	0.72 GiB
Q4_K_M	1.03 GiB	1.18 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	OpenCaption-2B-VL-SFT-v1.0	Qwen3.5-2B	Ratio
4,096	0.44 GiB	0.05 GiB	9.33×
8,192	0.88 GiB	0.09 GiB	9.33×
16,384	1.75 GiB	0.19 GiB	9.33×
32,768	3.50 GiB	0.38 GiB	9.33×
65,536	7.00 GiB	0.75 GiB	9.33×
131,072	14.00 GiB	1.50 GiB	9.33×