Is Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT or Qwen3-1.7B smaller?

Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT is smaller at Q4_K_M: 0.45 GiB against 1.03 GiB.

Which uses less memory at long context?

Qwen3-1.7B — its KV cache at 32K context is 1.0x smaller, because of how its attention layers cache.

Model comparison

At Q4_K_M, Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT is the smaller download — 484,219,808 bytes against 1,107,409,472.

From the file· summed bytes, KV per layer

	Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT	Qwen3-1.7B
Parameters	752M	2.0B
Architecture	qwen3	qwen3
Layers	28	28
Native context	40,960	40,960
Mixture of experts	no	no
Quantizations published	4	48
Smallest quantization	0.45 GiB	0.50 GiB
Q4_K_M	0.45 GiB	1.03 GiB
Licence	apache-2.0	—

the term that decides long-context viability

Context	Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT	Qwen3-1.7B	Ratio
4,096	0.44 GiB	0.44 GiB	1.00×
8,192	0.88 GiB	0.88 GiB	1.00×
16,384	1.75 GiB	1.75 GiB	1.00×
32,768	3.50 GiB	3.50 GiB	1.00×
65,536	7.00 GiB	7.00 GiB	1.00×
131,072	14.00 GiB	14.00 GiB	1.00×