Is Qwen3-Coder-30B-A3B-Instruct or Wizard-Vicuna-30B-Uncensored smaller?

Qwen3-Coder-30B-A3B-Instruct is smaller at Q4_K_M: 17.28 GiB against 18.27 GiB.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 16.3x smaller, because of how its attention layers cache.

Model comparison

Qwen3-Coder-30B-A3B-Instruct vs Wizard-Vicuna-30B-Uncensored

At Q4_K_M, Qwen3-Coder-30B-A3B-Instruct is the smaller download — 18,556,689,568 bytes against 19,621,139,904. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 16.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-Coder-30B-A3B-Instruct	Wizard-Vicuna-30B-Uncensored
Parameters	30.5B	32.5B
Architecture	qwen3moe	llama
Layers	48	60
Native context	262,144	2,048
Mixture of experts	yes, 128 experts	no
Quantizations published	46	33
Smallest quantization	7.46 GiB	6.63 GiB
Q4_K_M	17.28 GiB	18.27 GiB
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

Context	Qwen3-Coder-30B-A3B-Instruct	Wizard-Vicuna-30B-Uncensored	Ratio
4,096	0.38 GiB	6.09 GiB	16.25×
8,192	0.75 GiB	12.19 GiB	16.25×
16,384	1.50 GiB	24.38 GiB	16.25×
32,768	3.00 GiB	48.75 GiB	16.25×
65,536	6.00 GiB	97.50 GiB	16.25×
131,072	12.00 GiB	195.00 GiB	16.25×