Is Qwen3.6-27B or Nous-Capybara-limarpv3-34B smaller?

Qwen3.6-27B is smaller at Q4_K_M: 15.41 GiB against 19.24 GiB.

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 3.7x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs Nous-Capybara-limarpv3-34B

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 20,658,710,528. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 3.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-27B	Nous-Capybara-limarpv3-34B
Parameters	27.8B	34.4B
Architecture	qwen35	llama
Layers	64	60
Native context	262,144	200,000
Mixture of experts	no	no
Quantizations published	40	33
Smallest quantization	8.74 GiB	7.54 GiB
Q4_K_M	15.41 GiB	19.24 GiB
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	Nous-Capybara-limarpv3-34B	Ratio
4,096	0.25 GiB	0.94 GiB	3.75×
8,192	0.50 GiB	1.88 GiB	3.75×
16,384	1.00 GiB	3.75 GiB	3.75×
32,768	2.00 GiB	7.50 GiB	3.75×
65,536	4.00 GiB	15.00 GiB	3.75×
131,072	8.00 GiB	30.00 GiB	3.75×