Is GLM-5.2 or Qwen3-235B-A22B smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

GLM-5.2 — its KV cache at 32K context is 2.1x smaller, because of how its attention layers cache.

Model comparison

GLM-5.2 vs Qwen3-235B-A22B

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: GLM-5.2's KV cache at 32K is 2.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	GLM-5.2	Qwen3-235B-A22B
Parameters	753B	235B
Architecture	glm-dsa	qwen3moe
Layers	78	94
Native context	1,048,576	40,960
Mixture of experts	yes, 256 experts	yes, 128 experts
Quantizations published	20	35
Smallest quantization	169.33 GiB	79.81 GiB
Q4_K_M	—	132.39 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	GLM-5.2	Qwen3-235B-A22B	Ratio
4,096	0.34 GiB	0.73 GiB	2.14×
8,192	0.69 GiB	1.47 GiB	2.14×
16,384	1.37 GiB	2.94 GiB	2.14×
32,768	2.74 GiB	5.88 GiB	2.14×
65,536	5.48 GiB	11.75 GiB	2.14×
131,072	10.97 GiB	23.50 GiB	2.14×