Is Qwen3-Coder-30B-A3B-Instruct or Qwen3-15B-A2B-Base smaller?

Qwen3-15B-A2B-Base is smaller at Q4_K_M: 8.84 GiB against 17.28 GiB.

Which uses less memory at long context?

Qwen3-15B-A2B-Base — its KV cache at 32K context is 2.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3-Coder-30B-A3B-Instruct vs Qwen3-15B-A2B-Base

At Q4_K_M, Qwen3-15B-A2B-Base is the smaller download — 9,496,453,792 bytes against 18,556,689,568. At long context the gap widens: Qwen3-15B-A2B-Base'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-Coder-30B-A3B-Instruct	Qwen3-15B-A2B-Base
Parameters	30.5B	15.6B
Architecture	qwen3moe	qwen3moe
Layers	48	24
Native context	262,144	4,096
Mixture of experts	yes, 128 experts	yes, 128 experts
Quantizations published	46	11
Smallest quantization	7.46 GiB	5.41 GiB
Q4_K_M	17.28 GiB	8.84 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-Coder-30B-A3B-Instruct	Qwen3-15B-A2B-Base	Ratio
4,096	0.38 GiB	0.19 GiB	2.00×
8,192	0.75 GiB	0.38 GiB	2.00×
16,384	1.50 GiB	0.75 GiB	2.00×
32,768	3.00 GiB	1.50 GiB	2.00×
65,536	6.00 GiB	3.00 GiB	2.00×
131,072	12.00 GiB	6.00 GiB	2.00×