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

Ling-lite is smaller at Q4_K_M: 10.41 GiB against 17.28 GiB.

Which uses less memory at long context?

Ling-lite — its KV cache at 32K context is 1.7x smaller, because of how its attention layers cache.

Model comparison

Ling-lite vs Qwen3-30B-A3B-Thinking-2507

At Q4_K_M, Ling-lite is the smaller download — 11,175,490,944 bytes against 18,556,685,824. At long context the gap widens: Ling-lite's KV cache at 32K is 1.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Ling-lite	Qwen3-30B-A3B-Thinking-2507
Parameters	16.8B	30.5B
Architecture	bailingmoe	qwen3moe
Layers	28	48
Native context	32,768	262,144
Mixture of experts	yes, 64 experts	yes, 128 experts
Quantizations published	54	51
Smallest quantization	5.97 GiB	7.05 GiB
Q4_K_M	10.41 GiB	17.28 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Ling-lite	Qwen3-30B-A3B-Thinking-2507	Ratio
4,096	0.22 GiB	0.38 GiB	1.71×
8,192	0.44 GiB	0.75 GiB	1.71×
16,384	0.88 GiB	1.50 GiB	1.71×
32,768	1.75 GiB	3.00 GiB	1.71×
65,536	3.50 GiB	6.00 GiB	1.71×
131,072	7.00 GiB	12.00 GiB	1.71×