Is Qwen3.8-27B or Qwen3.5-9B-Nikusui-v1 smaller?

Qwen3.5-9B-Nikusui-v1 is smaller at Q4_K_M: 5.38 GiB against 15.66 GiB.

Which uses less memory at long context?

Qwen3.5-9B-Nikusui-v1 — its KV cache at 32K context is 2.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.8-27B vs Qwen3.5-9B-Nikusui-v1

At Q4_K_M, Qwen3.5-9B-Nikusui-v1 is the smaller download — 5,780,090,272 bytes against 16,810,714,336. At long context the gap widens: Qwen3.5-9B-Nikusui-v1's KV cache at 32K is 2.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.8-27B	Qwen3.5-9B-Nikusui-v1
Parameters	27.8B	9.7B
Architecture	qwen35	qwen35
Layers	64	32
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	22	29
Smallest quantization	8.39 GiB	3.65 GiB
Q4_K_M	15.66 GiB	5.38 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.8-27B	Qwen3.5-9B-Nikusui-v1	Ratio
4,096	0.25 GiB	0.13 GiB	2.00×
8,192	0.50 GiB	0.25 GiB	2.00×
16,384	1.00 GiB	0.50 GiB	2.00×
32,768	2.00 GiB	1.00 GiB	2.00×
65,536	4.00 GiB	2.00 GiB	2.00×
131,072	8.00 GiB	4.00 GiB	2.00×