Is SmolLM2-1.7B-Instruct-Uncensored or gemma-3-1b-it smaller?

gemma-3-1b-it is smaller at Q4_K_M: 0.75 GiB against 1.04 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 41.0x smaller, because of how its attention layers cache.

Model comparison

SmolLM2-1.7B-Instruct-Uncensored vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 1,112,233,344. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 41.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	SmolLM2-1.7B-Instruct-Uncensored	gemma-3-1b-it
Parameters	1.8B	1000M
Architecture	llama	gemma3
Layers	24	26
Native context	8,192	32,768
Mixture of experts	no	no
Quantizations published	12	28
Smallest quantization	0.66 GiB	0.52 GiB
Q4_K_M	1.04 GiB	0.75 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	SmolLM2-1.7B-Instruct-Uncensored	gemma-3-1b-it	Ratio
4,096	0.75 GiB	0.04 GiB	20.21×
8,192	1.50 GiB	0.05 GiB	28.44×
16,384	3.00 GiB	0.08 GiB	35.72×
32,768	6.00 GiB	0.15 GiB	40.96×
65,536	12.00 GiB	0.27 GiB	44.20×
131,072	24.00 GiB	0.52 GiB	46.02×