Is Moonlight-16B-A3B-Instruct or Qwen3.8-27B smaller?

Moonlight-16B-A3B-Instruct is smaller at Q4_K_M: 9.81 GiB against 15.66 GiB.

Which uses less memory at long context?

Moonlight-16B-A3B-Instruct — its KV cache at 32K context is 2.1x smaller, because of how its attention layers cache.

Model comparison

Moonlight-16B-A3B-Instruct vs Qwen3.8-27B

At Q4_K_M, Moonlight-16B-A3B-Instruct is the smaller download — 10,537,205,632 bytes against 16,810,714,336. At long context the gap widens: Moonlight-16B-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

	Moonlight-16B-A3B-Instruct	Qwen3.8-27B
Parameters	16.0B	27.8B
Architecture	deepseek2	qwen35
Layers	27	64
Native context	8,192	262,144
Mixture of experts	yes, 64 experts	no
Quantizations published	48	22
Smallest quantization	4.77 GiB	8.39 GiB
Q4_K_M	9.81 GiB	15.66 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Moonlight-16B-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×