Is Nethena-20B or Qwen3.6-27B smaller?

Nethena-20B is smaller at Q4_K_M: 11.22 GiB against 15.41 GiB.

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 19.4x smaller, because of how its attention layers cache.

Model comparison

Nethena-20B vs Qwen3.6-27B

At Q4_K_M, Nethena-20B is the smaller download — 12,042,208,800 bytes against 16,547,397,888. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 19.4× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Nethena-20B	Qwen3.6-27B
Parameters	20.0B	27.8B
Architecture	llama	qwen35
Layers	62	64
Native context	4,096	262,144
Mixture of experts	no	no
Quantizations published	12	40
Smallest quantization	7.74 GiB	8.74 GiB
Q4_K_M	11.22 GiB	15.41 GiB
Licence	cc-by-nc-4.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Nethena-20B	Qwen3.6-27B	Ratio
4,096	4.84 GiB	0.25 GiB	19.36×
8,192	9.69 GiB	0.50 GiB	19.37×
16,384	19.38 GiB	1.00 GiB	19.37×
32,768	38.75 GiB	2.00 GiB	19.37×
65,536	77.50 GiB	4.00 GiB	19.37×
131,072	155.00 GiB	8.00 GiB	19.37×