Is gemma-4-12B-it or chandra-ocr-2 smaller?

chandra-ocr-2 is smaller at Q4_K_M: 2.86 GiB against 6.63 GiB.

Which uses less memory at long context?

chandra-ocr-2 — its KV cache at 32K context is 2.5x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it vs chandra-ocr-2

At Q4_K_M, chandra-ocr-2 is the smaller download — 3,066,384,992 bytes against 7,121,861,440. At long context the gap widens: chandra-ocr-2's KV cache at 32K is 2.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-4-12B-it	chandra-ocr-2
Parameters	12.0B	5.3B
Architecture	gemma4	qwen35
Layers	48	32
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	59	14
Smallest quantization	3.92 GiB	1.98 GiB
Q4_K_M	6.63 GiB	2.86 GiB
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

Context	gemma-4-12B-it	chandra-ocr-2	Ratio
4,096	0.72 GiB	0.13 GiB	5.75×
8,192	0.97 GiB	0.25 GiB	3.87×
16,384	1.47 GiB	0.50 GiB	2.94×
32,768	2.47 GiB	1.00 GiB	2.47×
65,536	4.47 GiB	2.00 GiB	2.23×
131,072	8.47 GiB	4.00 GiB	2.12×