Is Kimi-Linear-48B-A3B-Instruct or Qwen3.8-27B smaller?

Qwen3.8-27B is smaller at Q4_K_M: 15.66 GiB against 27.66 GiB.

Which uses less memory at long context?

Kimi-Linear-48B-A3B-Instruct — its KV cache at 32K context is 2.1x smaller, because of how its attention layers cache.

Model comparison

Kimi-Linear-48B-A3B-Instruct vs Qwen3.8-27B

At Q4_K_M, Qwen3.8-27B is the smaller download — 16,810,714,336 bytes against 29,702,758,784. At long context the gap widens: Kimi-Linear-48B-A3B-Instruct's KV cache at 32K is 2.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Kimi-Linear-48B-A3B-Instruct	Qwen3.8-27B
Parameters	49.1B	27.8B
Architecture	kimi-linear	qwen35
Layers	27	64
Native context	—	262,144
Mixture of experts	yes, 256 experts	no
Quantizations published	38	22
Smallest quantization	9.77 GiB	8.39 GiB
Q4_K_M	27.66 GiB	15.66 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Kimi-Linear-48B-A3B-Instruct	Qwen3.8-27B	Ratio
4,096	0.12 GiB	0.25 GiB	2.11×
8,192	0.24 GiB	0.50 GiB	2.11×
16,384	0.47 GiB	1.00 GiB	2.11×
32,768	0.95 GiB	2.00 GiB	2.11×
65,536	1.90 GiB	4.00 GiB	2.11×
131,072	3.80 GiB	8.00 GiB	2.11×