Is Apriel-1.6-15b-Thinker or gemma-4-12B-it smaller?

gemma-4-12B-it is smaller at Q4_K_M: 6.63 GiB against 8.18 GiB.

Which uses less memory at long context?

gemma-4-12B-it — its KV cache at 32K context is 2.4x smaller, because of how its attention layers cache.

Model comparison

Apriel-1.6-15b-Thinker vs gemma-4-12B-it

At Q4_K_M, gemma-4-12B-it is the smaller download — 7,121,861,440 bytes against 8,785,478,144. At long context the gap widens: gemma-4-12B-it's KV cache at 32K is 2.4× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Apriel-1.6-15b-Thinker	gemma-4-12B-it
Parameters	14.9B	12.0B
Architecture	llama	gemma4
Layers	48	48
Native context	262,400	262,144
Mixture of experts	no	no
Quantizations published	60	59
Smallest quantization	3.22 GiB	3.92 GiB
Q4_K_M	8.18 GiB	6.63 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Apriel-1.6-15b-Thinker	gemma-4-12B-it	Ratio
4,096	0.75 GiB	0.72 GiB	1.04×
8,192	1.50 GiB	0.97 GiB	1.55×
16,384	3.00 GiB	1.47 GiB	2.04×
32,768	6.00 GiB	2.47 GiB	2.43×
65,536	12.00 GiB	4.47 GiB	2.69×
131,072	24.00 GiB	8.47 GiB	2.83×