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

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

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

	command-r-35b-writer-v2	Qwen3-Coder-30B-A3B-Instruct
Parameters	35.0B	30.5B
Architecture	command-r	qwen3moe
Layers	40	48
Native context	8,192	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	34	46
Smallest quantization	7.94 GiB	7.46 GiB
Q4_K_M	20.05 GiB	17.28 GiB
Licence	cc-by-nc-4.0	apache-2.0

KV cache by context

the term that decides long-context viability

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