Is Ling-lite or gemma-4-12B-it-qat-q4_0-unquantized smaller?

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

Which uses less memory at long context?

Ling-lite — its KV cache at 32K context is 1.4x smaller, because of how its attention layers cache.

Model comparison

Ling-lite vs gemma-4-12B-it-qat-q4_0-unquantized

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Ling-lite's KV cache at 32K is 1.4× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Ling-lite	gemma-4-12B-it-qat-q4_0-unquantized
Parameters	16.8B	12.0B
Architecture	bailingmoe	gemma4
Layers	28	48
Native context	32,768	262,144
Mixture of experts	yes, 64 experts	no
Quantizations published	54	2
Smallest quantization	5.97 GiB	6.50 GiB
Q4_K_M	10.41 GiB	—
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Ling-lite	gemma-4-12B-it-qat-q4_0-unquantized	Ratio
4,096	0.22 GiB	0.72 GiB	3.29×
8,192	0.44 GiB	0.97 GiB	2.21×
16,384	0.88 GiB	1.47 GiB	1.68×
32,768	1.75 GiB	2.47 GiB	1.41×
65,536	3.50 GiB	4.47 GiB	1.28×
131,072	7.00 GiB	8.47 GiB	1.21×