Is Marco-Nano-Instruct or Qwen3-4B smaller?

Qwen3-4B is smaller at Q4_K_M: 2.33 GiB against 5.00 GiB.

Which uses less memory at long context?

Marco-Nano-Instruct — its KV cache at 32K context is 1.3x smaller, because of how its attention layers cache.

Model comparison

Marco-Nano-Instruct vs Qwen3-4B

At Q4_K_M, Qwen3-4B is the smaller download — 2,497,280,256 bytes against 5,371,989,536. At long context the gap widens: Marco-Nano-Instruct's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Marco-Nano-Instruct	Qwen3-4B
Parameters	8.0B	4.0B
Architecture	qwen3moe	qwen3
Layers	28	36
Native context	32,768	40,960
Mixture of experts	yes, 232 experts	no
Quantizations published	36	29
Smallest quantization	2.44 GiB	1.01 GiB
Q4_K_M	5.00 GiB	2.33 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Marco-Nano-Instruct	Qwen3-4B	Ratio
4,096	0.44 GiB	0.56 GiB	1.29×
8,192	0.88 GiB	1.13 GiB	1.29×
16,384	1.75 GiB	2.25 GiB	1.29×
32,768	3.50 GiB	4.50 GiB	1.29×
65,536	7.00 GiB	9.00 GiB	1.29×
131,072	14.00 GiB	18.00 GiB	1.29×