Is Llama-3.2-1B-Instruct or gemma-3-1b-it smaller?

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

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 6.8x smaller, because of how its attention layers cache.

Model comparison

Llama-3.2-1B-Instruct vs gemma-3-1b-it

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 807,690,688. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 6.8× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Llama-3.2-1B-Instruct	gemma-3-1b-it
Parameters	1.2B	1000M
Architecture	llama	gemma3
Layers	16	26
Native context	131,072	32,768
Mixture of experts	no	no
Quantizations published	39	28
Smallest quantization	0.39 GiB	0.52 GiB
Q4_K_M	0.75 GiB	0.75 GiB
Licence	—	gemma

KV cache by context

the term that decides long-context viability

Context	Llama-3.2-1B-Instruct	gemma-3-1b-it	Ratio
4,096	0.13 GiB	0.04 GiB	3.37×
8,192	0.25 GiB	0.05 GiB	4.74×
16,384	0.50 GiB	0.08 GiB	5.95×
32,768	1.00 GiB	0.15 GiB	6.83×
65,536	2.00 GiB	0.27 GiB	7.37×
131,072	4.00 GiB	0.52 GiB	7.67×