Is Phi-4-reasoning-plus 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 2.5x smaller, because of how its attention layers cache.

Model comparison

Phi-4-reasoning-plus 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 2.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Phi-4-reasoning-plus	gemma-4-12B-it-qat-q4_0-unquantized
Parameters	14.7B	12.0B
Architecture	phi3	gemma4
Layers	40	48
Native context	32,768	262,144
Mixture of experts	no	no
Quantizations published	46	2
Smallest quantization	3.33 GiB	6.50 GiB
Q4_K_M	8.43 GiB	—
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Phi-4-reasoning-plus	gemma-4-12B-it-qat-q4_0-unquantized	Ratio
4,096	0.78 GiB	0.72 GiB	1.09×
8,192	1.56 GiB	0.97 GiB	1.61×
16,384	3.13 GiB	1.47 GiB	2.13×
32,768	6.25 GiB	2.47 GiB	2.53×
65,536	12.50 GiB	4.47 GiB	2.80×
131,072	25.00 GiB	8.47 GiB	2.95×