Is dots.ocr or Qwen3-4B smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

dots.ocr — its KV cache at 32K context is 5.1x smaller, because of how its attention layers cache.

Model comparison

dots.ocr vs Qwen3-4B

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: dots.ocr's KV cache at 32K is 5.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	dots.ocr	Qwen3-4B
Parameters	3.0B	4.0B
Architecture	qwen2	qwen3
Layers	28	36
Native context	131,072	40,960
Mixture of experts	no	no
Quantizations published	28	29
Smallest quantization	0.48 GiB	1.01 GiB
Q4_K_M	—	2.33 GiB
Licence	mit	—

KV cache by context

the term that decides long-context viability

Context	dots.ocr	Qwen3-4B	Ratio
4,096	0.11 GiB	0.56 GiB	5.14×
8,192	0.22 GiB	1.13 GiB	5.14×
16,384	0.44 GiB	2.25 GiB	5.14×
32,768	0.88 GiB	4.50 GiB	5.14×
65,536	1.75 GiB	9.00 GiB	5.14×
131,072	3.50 GiB	18.00 GiB	5.14×