Is qwen2.5-7b-bnb-4bit or Qwen3-30B-A3B-Thinking-2507 smaller?

qwen2.5-7b-bnb-4bit is smaller at Q4_K_M: 4.36 GiB against 17.28 GiB.

Which uses less memory at long context?

qwen2.5-7b-bnb-4bit — its KV cache at 32K context is 1.7x smaller, because of how its attention layers cache.

Model comparison

qwen2.5-7b-bnb-4bit vs Qwen3-30B-A3B-Thinking-2507

At Q4_K_M, qwen2.5-7b-bnb-4bit is the smaller download — 4,683,070,944 bytes against 18,556,685,824. At long context the gap widens: qwen2.5-7b-bnb-4bit'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

	qwen2.5-7b-bnb-4bit	Qwen3-30B-A3B-Thinking-2507
Parameters	7.8B	30.5B
Architecture	qwen2	qwen3moe
Layers	28	48
Native context	131,072	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	6	51
Smallest quantization	4.36 GiB	7.05 GiB
Q4_K_M	4.36 GiB	17.28 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	qwen2.5-7b-bnb-4bit	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×