Is Qwen3-Coder-30B-A3B-Instruct or Llama-3_1-Nemotron-51B-Instruct smaller?

Qwen3-Coder-30B-A3B-Instruct is smaller at Q4_K_M: 17.28 GiB against 28.91 GiB.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 26.7x smaller, because of how its attention layers cache.

Model comparison

Qwen3-Coder-30B-A3B-Instruct vs Llama-3_1-Nemotron-51B-Instruct

At Q4_K_M, Qwen3-Coder-30B-A3B-Instruct is the smaller download — 18,556,689,568 bytes against 31,037,307,136. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 26.7× 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	Llama-3_1-Nemotron-51B-Instruct
Parameters	30.5B	51.5B
Architecture	qwen3moe	deci
Layers	48	80
Native context	262,144	131,072
Mixture of experts	yes, 128 experts	no
Quantizations published	46	25
Smallest quantization	7.46 GiB	13.07 GiB
Q4_K_M	17.28 GiB	28.91 GiB
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

Context	Qwen3-Coder-30B-A3B-Instruct	Llama-3_1-Nemotron-51B-Instruct	Ratio
4,096	0.38 GiB	10.00 GiB	26.67×
8,192	0.75 GiB	20.00 GiB	26.67×
16,384	1.50 GiB	40.00 GiB	26.67×
32,768	3.00 GiB	80.00 GiB	26.67×
65,536	6.00 GiB	160.00 GiB	26.67×
131,072	12.00 GiB	320.00 GiB	26.67×