Is Laguna-XS-2.1 or Qwen3.8-27B smaller?

Qwen3.8-27B is smaller at Q4_K_M: 15.66 GiB against 18.88 GiB.

Which uses less memory at long context?

Laguna-XS-2.1 — its KV cache at 32K context is 1.5x smaller, because of how its attention layers cache.

Model comparison

Laguna-XS-2.1 vs Qwen3.8-27B

At Q4_K_M, Qwen3.8-27B is the smaller download — 16,810,714,336 bytes against 20,274,299,936. At long context the gap widens: Laguna-XS-2.1's KV cache at 32K is 1.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Laguna-XS-2.1	Qwen3.8-27B
Parameters	33.4B	27.8B
Architecture	laguna	qwen35
Layers	40	64
Native context	262,144	262,144
Mixture of experts	yes, 256 experts	no
Quantizations published	31	22
Smallest quantization	8.76 GiB	8.39 GiB
Q4_K_M	18.88 GiB	15.66 GiB
Licence	openmdw-1.1	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Laguna-XS-2.1	Qwen3.8-27B	Ratio
4,096	0.27 GiB	0.25 GiB	1.09×
8,192	0.43 GiB	0.50 GiB	1.16×
16,384	0.74 GiB	1.00 GiB	1.35×
32,768	1.37 GiB	2.00 GiB	1.46×
65,536	2.62 GiB	4.00 GiB	1.53×
131,072	5.12 GiB	8.00 GiB	1.56×