Is gemma-3-270m-it-qat or Llama-3.2-1B-Instruct smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

gemma-3-270m-it-qat — its KV cache at 32K context is 9.2x smaller, because of how its attention layers cache.

Model comparison

gemma-3-270m-it-qat vs Llama-3.2-1B-Instruct

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-3-270m-it-qat's KV cache at 32K is 9.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-3-270m-it-qat	Llama-3.2-1B-Instruct
Parameters	268M	1.2B
Architecture	gemma3	llama
Layers	18	16
Native context	32,768	131,072
Mixture of experts	no	no
Quantizations published	1	39
Smallest quantization	0.22 GiB	0.39 GiB
Q4_K_M	—	0.75 GiB
Licence	—	—

KV cache by context

the term that decides long-context viability

Context	gemma-3-270m-it-qat	Llama-3.2-1B-Instruct	Ratio
4,096	0.03 GiB	0.13 GiB	4.74×
8,192	0.04 GiB	0.25 GiB	6.56×
16,384	0.06 GiB	0.50 GiB	8.13×
32,768	0.11 GiB	1.00 GiB	9.23×
65,536	0.20 GiB	2.00 GiB	9.89×
131,072	0.39 GiB	4.00 GiB	10.27×