Is Qwen3.8-27B or Noromaid-20b-v0.1.1 smaller?

Noromaid-20b-v0.1.1 is smaller at Q4_K_M: 11.22 GiB against 15.66 GiB.

Which uses less memory at long context?

Qwen3.8-27B — its KV cache at 32K context is 19.4x smaller, because of how its attention layers cache.

Model comparison

Qwen3.8-27B vs Noromaid-20b-v0.1.1

At Q4_K_M, Noromaid-20b-v0.1.1 is the smaller download — 12,042,208,864 bytes against 16,810,714,336. At long context the gap widens: Qwen3.8-27B'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

	Qwen3.8-27B	Noromaid-20b-v0.1.1
Parameters	27.8B	20.0B
Architecture	qwen35	llama
Layers	64	62
Native context	262,144	4,096
Mixture of experts	no	no
Quantizations published	22	33
Smallest quantization	8.39 GiB	4.09 GiB
Q4_K_M	15.66 GiB	11.22 GiB
Licence	apache-2.0	cc-by-nc-4.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.8-27B	Noromaid-20b-v0.1.1	Ratio
4,096	0.25 GiB	4.84 GiB	19.36×
8,192	0.50 GiB	9.69 GiB	19.37×
16,384	1.00 GiB	19.38 GiB	19.37×
32,768	2.00 GiB	38.75 GiB	19.37×
65,536	4.00 GiB	77.50 GiB	19.37×
131,072	8.00 GiB	155.00 GiB	19.37×