Is Qwen3.6-27B or Vikhr-Nemo-12B-Instruct-R-21-09-24 smaller?

Vikhr-Nemo-12B-Instruct-R-21-09-24 is smaller at Q4_K_M: 6.96 GiB against 15.41 GiB.

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 2.5x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs Vikhr-Nemo-12B-Instruct-R-21-09-24

At Q4_K_M, Vikhr-Nemo-12B-Instruct-R-21-09-24 is the smaller download — 7,477,218,656 bytes against 16,547,397,888. At long context the gap widens: Qwen3.6-27B'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

	Qwen3.6-27B	Vikhr-Nemo-12B-Instruct-R-21-09-24
Parameters	27.8B	12.2B
Architecture	qwen35	llama
Layers	64	40
Native context	262,144	1,024,000
Mixture of experts	no	no
Quantizations published	40	22
Smallest quantization	8.74 GiB	4.13 GiB
Q4_K_M	15.41 GiB	6.96 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	Vikhr-Nemo-12B-Instruct-R-21-09-24	Ratio
4,096	0.25 GiB	0.63 GiB	2.50×
8,192	0.50 GiB	1.25 GiB	2.50×
16,384	1.00 GiB	2.50 GiB	2.50×
32,768	2.00 GiB	5.00 GiB	2.50×
65,536	4.00 GiB	10.00 GiB	2.50×
131,072	8.00 GiB	20.00 GiB	2.50×