Is dots.ocr or gemma-3-1b-it smaller?

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

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 6.0x smaller, because of how its attention layers cache.

Model comparison

dots.ocr vs gemma-3-1b-it

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 6.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	dots.ocr	gemma-3-1b-it
Parameters	3.0B	1000M
Architecture	qwen2	gemma3
Layers	28	26
Native context	131,072	32,768
Mixture of experts	no	no
Quantizations published	28	28
Smallest quantization	0.48 GiB	0.52 GiB
Q4_K_M	—	0.75 GiB
Licence	mit	gemma

KV cache by context

the term that decides long-context viability

Context	dots.ocr	gemma-3-1b-it	Ratio
4,096	0.11 GiB	0.04 GiB	2.95×
8,192	0.22 GiB	0.05 GiB	4.15×
16,384	0.44 GiB	0.08 GiB	5.21×
32,768	0.88 GiB	0.15 GiB	5.97×
65,536	1.75 GiB	0.27 GiB	6.45×
131,072	3.50 GiB	0.52 GiB	6.71×