Is Qwen3-Coder-30B-A3B-Instruct or command-r-35b-writer-v2 smaller?

Qwen3-Coder-30B-A3B-Instruct is smaller at Q4_K_M: 17.28 GiB against 20.05 GiB.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 13.3x smaller, because of how its attention layers cache.

Model comparison

Qwen3-Coder-30B-A3B-Instruct vs command-r-35b-writer-v2

At Q4_K_M, Qwen3-Coder-30B-A3B-Instruct is the smaller download — 18,556,689,568 bytes against 21,527,056,288. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 13.3× 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	command-r-35b-writer-v2
Parameters	30.5B	35.0B
Architecture	qwen3moe	command-r
Layers	48	40
Native context	262,144	8,192
Mixture of experts	yes, 128 experts	no
Quantizations published	46	34
Smallest quantization	7.46 GiB	7.94 GiB
Q4_K_M	17.28 GiB	20.05 GiB
Licence	apache-2.0	cc-by-nc-4.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-Coder-30B-A3B-Instruct	command-r-35b-writer-v2	Ratio
4,096	0.38 GiB	5.00 GiB	13.33×
8,192	0.75 GiB	10.00 GiB	13.33×
16,384	1.50 GiB	20.00 GiB	13.33×
32,768	3.00 GiB	40.00 GiB	13.33×
65,536	6.00 GiB	80.00 GiB	13.33×
131,072	12.00 GiB	160.00 GiB	13.33×