Is granite-4.0-h-350m or gemma-3-270m-it smaller?

granite-4.0-h-350m is smaller at Q4_K_M: 0.21 GiB against 0.24 GiB.

Which uses less memory at long context?

gemma-3-270m-it — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

granite-4.0-h-350m vs gemma-3-270m-it

At Q4_K_M, granite-4.0-h-350m is the smaller download — 222,662,560 bytes against 253,115,168. At long context the gap widens: gemma-3-270m-it's KV cache at 32K is 1.2× 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-350m	gemma-3-270m-it
Parameters	340M	268M
Architecture	granitehybrid	gemma3
Layers	32	18
Native context	32,768	32,768
Mixture of experts	no	no
Quantizations published	29	39
Smallest quantization	0.15 GiB	0.17 GiB
Q4_K_M	0.21 GiB	0.24 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	granite-4.0-h-350m	gemma-3-270m-it	Ratio
4,096	0.02 GiB	0.03 GiB	1.68×
8,192	0.03 GiB	0.04 GiB	1.22×
16,384	0.06 GiB	0.06 GiB	1.02×
32,768	0.13 GiB	0.11 GiB	1.15×
65,536	0.25 GiB	0.20 GiB	1.24×
131,072	0.50 GiB	0.39 GiB	1.28×