Is Qwen3.5-9B or pixtral-12b smaller?

Qwen3.5-9B is smaller at Q4_K_M: 5.24 GiB against 6.96 GiB.

Which uses less memory at long context?

Qwen3.5-9B — its KV cache at 32K context is 5.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-9B vs pixtral-12b

At Q4_K_M, Qwen3.5-9B is the smaller download — 5,627,044,256 bytes against 7,477,204,608. At long context the gap widens: Qwen3.5-9B's KV cache at 32K is 5.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-9B	pixtral-12b
Parameters	9.7B	12.7B
Architecture	qwen35	llama
Layers	32	40
Native context	262,144	1,024,000
Mixture of experts	no	no
Quantizations published	34	32
Smallest quantization	2.97 GiB	3.85 GiB
Q4_K_M	5.24 GiB	6.96 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-9B	pixtral-12b	Ratio
4,096	0.13 GiB	0.63 GiB	5.00×
8,192	0.25 GiB	1.25 GiB	5.00×
16,384	0.50 GiB	2.50 GiB	5.00×
32,768	1.00 GiB	5.00 GiB	5.00×
65,536	2.00 GiB	10.00 GiB	5.00×
131,072	4.00 GiB	20.00 GiB	5.00×