Is NEXUS-Coder or Qwen3-0.6B smaller?

Qwen3-0.6B is smaller at Q4_K_M: 0.37 GiB against 0.92 GiB.

Which uses less memory at long context?

NEXUS-Coder — its KV cache at 32K context is 4.0x smaller, because of how its attention layers cache.

Model comparison

NEXUS-Coder vs Qwen3-0.6B

At Q4_K_M, Qwen3-0.6B is the smaller download — 396,705,472 bytes against 986,045,472. At long context the gap widens: NEXUS-Coder's KV cache at 32K is 4.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	NEXUS-Coder	Qwen3-0.6B
Parameters	1.5B	752M
Architecture	qwen2	qwen3
Layers	28	28
Native context	32,768	40,960
Mixture of experts	no	no
Quantizations published	23	44
Smallest quantization	0.29 GiB	0.20 GiB
Q4_K_M	0.92 GiB	0.37 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	NEXUS-Coder	Qwen3-0.6B	Ratio
4,096	0.11 GiB	0.44 GiB	4.00×
8,192	0.22 GiB	0.88 GiB	4.00×
16,384	0.44 GiB	1.75 GiB	4.00×
32,768	0.88 GiB	3.50 GiB	4.00×
65,536	1.75 GiB	7.00 GiB	4.00×
131,072	3.50 GiB	14.00 GiB	4.00×