Is granite-vision-4.1-4b or gemma-4-E4B-it smaller?

granite-vision-4.1-4b is smaller at Q4_K_M: 1.96 GiB against 4.64 GiB.

Which uses less memory at long context?

gemma-4-E4B-it — its KV cache at 32K context is 4.9x smaller, because of how its attention layers cache.

Model comparison

granite-vision-4.1-4b vs gemma-4-E4B-it

At Q4_K_M, granite-vision-4.1-4b is the smaller download — 2,099,510,240 bytes against 4,977,171,584. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 4.9× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	granite-vision-4.1-4b	gemma-4-E4B-it
Parameters	4.0B	8.0B
Architecture	granite	gemma4
Layers	40	42
Native context	131,072	131,072
Mixture of experts	no	no
Quantizations published	5	36
Smallest quantization	1.96 GiB	3.30 GiB
Q4_K_M	1.96 GiB	4.64 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	granite-vision-4.1-4b	gemma-4-E4B-it	Ratio
4,096	0.31 GiB	0.12 GiB	2.54×
8,192	0.63 GiB	0.18 GiB	3.52×
16,384	1.25 GiB	0.29 GiB	4.35×
32,768	2.50 GiB	0.51 GiB	4.94×
65,536	5.00 GiB	0.94 GiB	5.30×
131,072	10.00 GiB	1.82 GiB	5.50×