Is gemma-4-12B-it-qat-q4_0-unquantized or Llama-2-13b-chat-hf 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 10.1x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it-qat-q4_0-unquantized vs Llama-2-13b-chat-hf

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 10.1× 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	Llama-2-13b-chat-hf
Parameters	12.0B	13.0B
Architecture	gemma4	llama
Layers	48	40
Native context	262,144	4,096
Mixture of experts	no	no
Quantizations published	2	25
Smallest quantization	6.50 GiB	5.06 GiB
Q4_K_M	—	7.33 GiB
Licence	apache-2.0	llama2

KV cache by context

the term that decides long-context viability

Context	gemma-4-12B-it-qat-q4_0-unquantized	Llama-2-13b-chat-hf	Ratio
4,096	0.72 GiB	3.13 GiB	4.35×
8,192	0.97 GiB	6.25 GiB	6.45×
16,384	1.47 GiB	12.50 GiB	8.51×
32,768	2.47 GiB	25.00 GiB	10.13×
65,536	4.47 GiB	50.00 GiB	11.19×
131,072	8.47 GiB	100.00 GiB	11.81×