Is Ling-mini-2.0 or Qwen3-30B-A3B-Thinking-2507 smaller?

Ling-mini-2.0 is smaller at Q4_K_M: 9.23 GiB against 17.28 GiB.

Which uses less memory at long context?

Ling-mini-2.0 — its KV cache at 32K context is 2.4x smaller, because of how its attention layers cache.

Model comparison

Ling-mini-2.0 vs Qwen3-30B-A3B-Thinking-2507

At Q4_K_M, Ling-mini-2.0 is the smaller download — 9,911,575,072 bytes against 18,556,685,824. At long context the gap widens: Ling-mini-2.0's KV cache at 32K is 2.4× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Ling-mini-2.0	Qwen3-30B-A3B-Thinking-2507
Parameters	16.3B	30.5B
Architecture	bailingmoe2	qwen3moe
Layers	20	48
Native context	32,768	262,144
Mixture of experts	yes, 256 experts	yes, 128 experts
Quantizations published	30	51
Smallest quantization	4.34 GiB	7.05 GiB
Q4_K_M	9.23 GiB	17.28 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Ling-mini-2.0	Qwen3-30B-A3B-Thinking-2507	Ratio
4,096	0.16 GiB	0.38 GiB	2.40×
8,192	0.31 GiB	0.75 GiB	2.40×
16,384	0.63 GiB	1.50 GiB	2.40×
32,768	1.25 GiB	3.00 GiB	2.40×
65,536	2.50 GiB	6.00 GiB	2.40×
131,072	5.00 GiB	12.00 GiB	2.40×