Is Kimi-VL-A3B-Thinking-2506 or Qwen3-30B-A3B-Thinking-2507 smaller?

Kimi-VL-A3B-Thinking-2506 is smaller at Q4_K_M: 9.82 GiB against 17.28 GiB.

Which uses less memory at long context?

Kimi-VL-A3B-Thinking-2506 — its KV cache at 32K context is 3.2x smaller, because of how its attention layers cache.

Model comparison

Kimi-VL-A3B-Thinking-2506 vs Qwen3-30B-A3B-Thinking-2507

At Q4_K_M, Kimi-VL-A3B-Thinking-2506 is the smaller download — 10,540,747,680 bytes against 18,556,685,824. At long context the gap widens: Kimi-VL-A3B-Thinking-2506's KV cache at 32K is 3.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Kimi-VL-A3B-Thinking-2506	Qwen3-30B-A3B-Thinking-2507
Parameters	16.4B	30.5B
Architecture	deepseek2	qwen3moe
Layers	27	48
Native context	131,072	262,144
Mixture of experts	yes, 64 experts	yes, 128 experts
Quantizations published	21	51
Smallest quantization	6.13 GiB	7.05 GiB
Q4_K_M	9.82 GiB	17.28 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Kimi-VL-A3B-Thinking-2506	Qwen3-30B-A3B-Thinking-2507	Ratio
4,096	0.12 GiB	0.38 GiB	3.16×
8,192	0.24 GiB	0.75 GiB	3.16×
16,384	0.47 GiB	1.50 GiB	3.16×
32,768	0.95 GiB	3.00 GiB	3.16×
65,536	1.90 GiB	6.00 GiB	3.16×
131,072	3.80 GiB	12.00 GiB	3.16×