Is stable-code-3b or gemma-3-1b-it smaller?

gemma-3-1b-it is smaller at Q4_K_M: 0.75 GiB against 1.59 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 68.3x smaller, because of how its attention layers cache.

Model comparison

stable-code-3b vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 1,708,595,200. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 68.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	stable-code-3b	gemma-3-1b-it
Parameters	2.8B	1000M
Architecture	stablelm	gemma3
Layers	32	26
Native context	16,384	32,768
Mixture of experts	no	no
Quantizations published	48	28
Smallest quantization	0.63 GiB	0.52 GiB
Q4_K_M	1.59 GiB	0.75 GiB
Licence	other	gemma

KV cache by context

the term that decides long-context viability

Context	stable-code-3b	gemma-3-1b-it	Ratio
4,096	1.25 GiB	0.04 GiB	33.68×
8,192	2.50 GiB	0.05 GiB	47.41×
16,384	5.00 GiB	0.08 GiB	59.53×
32,768	10.00 GiB	0.15 GiB	68.27×
65,536	20.00 GiB	0.27 GiB	73.67×
131,072	40.00 GiB	0.52 GiB	76.70×