Is gemma-4-12B-it-qat-q4_0-unquantized or NousCoder-14B smaller?

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

Which uses less memory at long context?

gemma-4-12B-it-qat-q4_0-unquantized — its KV cache at 32K context is 2.0x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it-qat-q4_0-unquantized vs NousCoder-14B

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-4-12B-it-qat-q4_0-unquantized's KV cache at 32K is 2.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-4-12B-it-qat-q4_0-unquantized	NousCoder-14B
Parameters	12.0B	14.8B
Architecture	gemma4	qwen3
Layers	48	40
Native context	262,144	81,920
Mixture of experts	no	no
Quantizations published	2	26
Smallest quantization	6.50 GiB	4.37 GiB
Q4_K_M	—	8.38 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-12B-it-qat-q4_0-unquantized	NousCoder-14B	Ratio
4,096	0.72 GiB	0.63 GiB	1.15×
8,192	0.97 GiB	1.25 GiB	1.29×
16,384	1.47 GiB	2.50 GiB	1.70×
32,768	2.47 GiB	5.00 GiB	2.03×
65,536	4.47 GiB	10.00 GiB	2.24×
131,072	8.47 GiB	20.00 GiB	2.36×