Is Vikhr-Gemma-2B-instruct 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 12.7x smaller, because of how its attention layers cache.

Model comparison

Vikhr-Gemma-2B-instruct vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 1,708,582,848. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 12.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Vikhr-Gemma-2B-instruct	gemma-3-1b-it
Parameters	2.6B	1000M
Architecture	gemma2	gemma3
Layers	26	26
Native context	8,192	32,768
Mixture of experts	no	no
Quantizations published	46	28
Smallest quantization	0.78 GiB	0.52 GiB
Q4_K_M	1.59 GiB	0.75 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	Vikhr-Gemma-2B-instruct	gemma-3-1b-it	Ratio
4,096	0.41 GiB	0.04 GiB	10.95×
8,192	0.63 GiB	0.05 GiB	12.04×
16,384	1.04 GiB	0.08 GiB	12.40×
32,768	1.85 GiB	0.15 GiB	12.65×
65,536	3.48 GiB	0.27 GiB	12.81×
131,072	6.73 GiB	0.52 GiB	12.90×