Is Qwythos-9B-v2 or gemma-4-12B-it smaller?

Qwythos-9B-v2 is smaller at Q4_K_M: 5.63 GiB against 6.63 GiB.

Which uses less memory at long context?

Qwythos-9B-v2 — its KV cache at 32K context is 2.5x smaller, because of how its attention layers cache.

Model comparison

Qwythos-9B-v2 vs gemma-4-12B-it

At Q4_K_M, Qwythos-9B-v2 is the smaller download — 6,047,707,680 bytes against 7,121,861,440. At long context the gap widens: Qwythos-9B-v2'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

	Qwythos-9B-v2	gemma-4-12B-it
Parameters	9.7B	12.0B
Architecture	qwen35	gemma4
Layers	32	48
Native context	1,048,576	262,144
Mixture of experts	no	no
Quantizations published	43	59
Smallest quantization	3.64 GiB	3.92 GiB
Q4_K_M	5.63 GiB	6.63 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwythos-9B-v2	gemma-4-12B-it	Ratio
4,096	0.13 GiB	0.72 GiB	5.75×
8,192	0.25 GiB	0.97 GiB	3.87×
16,384	0.50 GiB	1.47 GiB	2.94×
32,768	1.00 GiB	2.47 GiB	2.47×
65,536	2.00 GiB	4.47 GiB	2.23×
131,072	4.00 GiB	8.47 GiB	2.12×