Is LLAMA-3_8B_Unaligned_BETA 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?

gemma-4-12B-it-qat-q4_0-unquantized — its KV cache at 32K context is 1.6x smaller, because of how its attention layers cache.

Model comparison

LLAMA-3_8B_Unaligned_BETA 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: gemma-4-12B-it-qat-q4_0-unquantized's KV cache at 32K is 1.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	LLAMA-3_8B_Unaligned_BETA	gemma-4-12B-it-qat-q4_0-unquantized
Parameters	8.0B	12.0B
Architecture	llama	gemma4
Layers	32	48
Native context	16,384	262,144
Mixture of experts	no	no
Quantizations published	20	2
Smallest quantization	2.75 GiB	6.50 GiB
Q4_K_M	4.58 GiB	—
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	LLAMA-3_8B_Unaligned_BETA	gemma-4-12B-it-qat-q4_0-unquantized	Ratio
4,096	0.50 GiB	0.72 GiB	1.44×
8,192	1.00 GiB	0.97 GiB	1.03×
16,384	2.00 GiB	1.47 GiB	1.36×
32,768	4.00 GiB	2.47 GiB	1.62×
65,536	8.00 GiB	4.47 GiB	1.79×
131,072	16.00 GiB	8.47 GiB	1.89×