Is granite-3.1-1b-a400m-instruct or gemma-3-1b-it smaller?

gemma-3-1b-it is smaller at Q4_K_M: 0.75 GiB against 0.77 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 10.2x smaller, because of how its attention layers cache.

Model comparison

granite-3.1-1b-a400m-instruct vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 821,847,360. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 10.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	granite-3.1-1b-a400m-instruct	gemma-3-1b-it
Parameters	1.3B	1000M
Architecture	granitemoe	gemma3
Layers	24	26
Native context	131,072	32,768
Mixture of experts	yes, 32 experts	no
Quantizations published	20	28
Smallest quantization	0.48 GiB	0.52 GiB
Q4_K_M	0.77 GiB	0.75 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	granite-3.1-1b-a400m-instruct	gemma-3-1b-it	Ratio
4,096	0.19 GiB	0.04 GiB	5.05×
8,192	0.38 GiB	0.05 GiB	7.11×
16,384	0.75 GiB	0.08 GiB	8.93×
32,768	1.50 GiB	0.15 GiB	10.24×
65,536	3.00 GiB	0.27 GiB	11.05×
131,072	6.00 GiB	0.52 GiB	11.51×