Is Financial-v1-2B or Qwen3-4B smaller?

Financial-v1-2B is smaller at Q4_K_M: 1.22 GiB against 2.33 GiB.

Which uses less memory at long context?

Financial-v1-2B — its KV cache at 32K context is 12.0x smaller, because of how its attention layers cache.

Model comparison

Financial-v1-2B vs Qwen3-4B

At Q4_K_M, Financial-v1-2B is the smaller download — 1,312,165,280 bytes against 2,497,280,256. At long context the gap widens: Financial-v1-2B's KV cache at 32K is 12.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Financial-v1-2B	Qwen3-4B
Parameters	1.9B	4.0B
Architecture	qwen35	qwen3
Layers	24	36
Native context	262,144	40,960
Mixture of experts	no	no
Quantizations published	27	29
Smallest quantization	0.92 GiB	1.01 GiB
Q4_K_M	1.22 GiB	2.33 GiB
Licence	—	—

KV cache by context

the term that decides long-context viability

Context	Financial-v1-2B	Qwen3-4B	Ratio
4,096	0.05 GiB	0.56 GiB	11.99×
8,192	0.09 GiB	1.13 GiB	12.00×
16,384	0.19 GiB	2.25 GiB	12.00×
32,768	0.38 GiB	4.50 GiB	12.00×
65,536	0.75 GiB	9.00 GiB	12.00×
131,072	1.50 GiB	18.00 GiB	12.00×