Is HunyuanOCR or gemma-3-1b-it smaller?

HunyuanOCR is smaller at Q4_K_M: 0.33 GiB against 0.75 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 5.8x smaller, because of how its attention layers cache.

Model comparison

HunyuanOCR vs gemma-3-1b-it

At Q4_K_M, HunyuanOCR is the smaller download — 354,966,656 bytes against 806,058,240. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 5.8× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	HunyuanOCR	gemma-3-1b-it
Parameters	1.1B	1000M
Architecture	hunyuan_vl	gemma3
Layers	24	26
Native context	131,072	32,768
Mixture of experts	yes, 1 experts	no
Quantizations published	25	28
Smallest quantization	0.24 GiB	0.52 GiB
Q4_K_M	0.33 GiB	0.75 GiB
Licence	—	gemma

KV cache by context

the term that decides long-context viability

Context	HunyuanOCR	gemma-3-1b-it	Ratio
4,096	0.11 GiB	0.04 GiB	2.84×
8,192	0.21 GiB	0.05 GiB	4.00×
16,384	0.42 GiB	0.08 GiB	5.02×
32,768	0.84 GiB	0.15 GiB	5.76×
65,536	1.69 GiB	0.27 GiB	6.22×
131,072	3.38 GiB	0.52 GiB	6.47×