Is Qwen2.5-VL-3B-Instruct or gemma-3-1b-it smaller?

gemma-3-1b-it is smaller at Q4_K_M: 0.75 GiB against 1.80 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 7.7x smaller, because of how its attention layers cache.

Model comparison

Qwen2.5-VL-3B-Instruct vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 1,929,901,056. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 7.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen2.5-VL-3B-Instruct	gemma-3-1b-it
Parameters	3.8B	1000M
Architecture	qwen2vl	gemma3
Layers	36	26
Native context	128,000	32,768
Mixture of experts	no	no
Quantizations published	27	28
Smallest quantization	0.77 GiB	0.52 GiB
Q4_K_M	1.80 GiB	0.75 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	Qwen2.5-VL-3B-Instruct	gemma-3-1b-it	Ratio
4,096	0.14 GiB	0.04 GiB	3.79×
8,192	0.28 GiB	0.05 GiB	5.33×
16,384	0.56 GiB	0.08 GiB	6.70×
32,768	1.13 GiB	0.15 GiB	7.68×
65,536	2.25 GiB	0.27 GiB	8.29×
131,072	4.50 GiB	0.52 GiB	8.63×