Is granite-3.2-2b-instruct or gemma-3-1b-it smaller?

gemma-3-1b-it is smaller at Q4_K_M: 0.75 GiB against 1.44 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 17.1x smaller, because of how its attention layers cache.

Model comparison

granite-3.2-2b-instruct vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 1,545,296,256. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 17.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	granite-3.2-2b-instruct	gemma-3-1b-it
Parameters	2.5B	1000M
Architecture	granite	gemma3
Layers	40	26
Native context	131,072	32,768
Mixture of experts	no	no
Quantizations published	52	28
Smallest quantization	0.83 GiB	0.52 GiB
Q4_K_M	1.44 GiB	0.75 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	granite-3.2-2b-instruct	gemma-3-1b-it	Ratio
4,096	0.31 GiB	0.04 GiB	8.42×
8,192	0.63 GiB	0.05 GiB	11.85×
16,384	1.25 GiB	0.08 GiB	14.88×
32,768	2.50 GiB	0.15 GiB	17.07×
65,536	5.00 GiB	0.27 GiB	18.42×
131,072	10.00 GiB	0.52 GiB	19.18×