Is GLM-Z1-Rumination-32B-0414 or Qwen3-Coder-30B-A3B-Instruct smaller?

Qwen3-Coder-30B-A3B-Instruct is smaller at Q4_K_M: 17.28 GiB against 18.66 GiB.

Which uses less memory at long context?

Qwen3-Coder-30B-A3B-Instruct — its KV cache at 32K context is 2.5x smaller, because of how its attention layers cache.

Model comparison

GLM-Z1-Rumination-32B-0414 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 20,040,332,576. At long context the gap widens: Qwen3-Coder-30B-A3B-Instruct's KV cache at 32K is 2.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	GLM-Z1-Rumination-32B-0414	Qwen3-Coder-30B-A3B-Instruct
Parameters	33.1B	30.5B
Architecture	glm4	qwen3moe
Layers	61	48
Native context	131,072	262,144
Mixture of experts	no	yes, 128 experts
Quantizations published	29	46
Smallest quantization	9.45 GiB	7.46 GiB
Q4_K_M	18.66 GiB	17.28 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	GLM-Z1-Rumination-32B-0414	Qwen3-Coder-30B-A3B-Instruct	Ratio
4,096	0.95 GiB	0.38 GiB	2.54×
8,192	1.91 GiB	0.75 GiB	2.54×
16,384	3.81 GiB	1.50 GiB	2.54×
32,768	7.63 GiB	3.00 GiB	2.54×
65,536	15.25 GiB	6.00 GiB	2.54×
131,072	30.50 GiB	12.00 GiB	2.54×