Is GLM-OCR or gemma-3-1b-it smaller?

GLM-OCR is smaller at Q4_K_M: 0.51 GiB against 0.75 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 13.7x smaller, because of how its attention layers cache.

Model comparison

GLM-OCR vs gemma-3-1b-it

At Q4_K_M, GLM-OCR is the smaller download — 548,515,136 bytes against 806,058,240. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 13.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	GLM-OCR	gemma-3-1b-it
Parameters	1.3B	1000M
Architecture	glm4	gemma3
Layers	16	26
Native context	131,072	32,768
Mixture of experts	no	no
Quantizations published	30	28
Smallest quantization	0.34 GiB	0.52 GiB
Q4_K_M	0.51 GiB	0.75 GiB
Licence	—	gemma

KV cache by context

the term that decides long-context viability

Context	GLM-OCR	gemma-3-1b-it	Ratio
4,096	0.25 GiB	0.04 GiB	6.74×
8,192	0.50 GiB	0.05 GiB	9.48×
16,384	1.00 GiB	0.08 GiB	11.91×
32,768	2.00 GiB	0.15 GiB	13.65×
65,536	4.00 GiB	0.27 GiB	14.73×
131,072	8.00 GiB	0.52 GiB	15.34×