Is granite-4.0-h-3b-ar or gemma-3-1b-it smaller?

gemma-3-1b-it is smaller at Q4_K_M: 0.75 GiB against 1.92 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 1.7x smaller, because of how its attention layers cache.

Model comparison

granite-4.0-h-3b-ar vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 2,058,170,400. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 1.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	granite-4.0-h-3b-ar	gemma-3-1b-it
Parameters	3.4B	1000M
Architecture	granitehybrid	gemma3
Layers	40	26
Native context	131,072	32,768
Mixture of experts	no	no
Quantizations published	36	28
Smallest quantization	0.76 GiB	0.52 GiB
Q4_K_M	1.92 GiB	0.75 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	granite-4.0-h-3b-ar	gemma-3-1b-it	Ratio
4,096	0.03 GiB	0.04 GiB	1.18×
8,192	0.06 GiB	0.05 GiB	1.19×
16,384	0.13 GiB	0.08 GiB	1.49×
32,768	0.25 GiB	0.15 GiB	1.71×
65,536	0.50 GiB	0.27 GiB	1.84×
131,072	1.00 GiB	0.52 GiB	1.92×