Is glm-4-9b-chat-1m or Qwen3.8-27B smaller?

glm-4-9b-chat-1m is smaller at Q4_K_M: 5.88 GiB against 15.66 GiB.

Which uses less memory at long context?

Qwen3.8-27B — its KV cache at 32K context is 10.0x smaller, because of how its attention layers cache.

Model comparison

glm-4-9b-chat-1m vs Qwen3.8-27B

At Q4_K_M, glm-4-9b-chat-1m is the smaller download — 6,308,679,680 bytes against 16,810,714,336. At long context the gap widens: Qwen3.8-27B's KV cache at 32K is 10.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	glm-4-9b-chat-1m	Qwen3.8-27B
Parameters	9.5B	27.8B
Architecture	chatglm	qwen35
Layers	40	64
Native context	—	262,144
Mixture of experts	no	no
Quantizations published	49	22
Smallest quantization	3.69 GiB	8.39 GiB
Q4_K_M	5.88 GiB	15.66 GiB
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	glm-4-9b-chat-1m	Qwen3.8-27B	Ratio
4,096	2.50 GiB	0.25 GiB	9.99×
8,192	5.00 GiB	0.50 GiB	10.00×
16,384	10.00 GiB	1.00 GiB	10.00×
32,768	20.00 GiB	2.00 GiB	10.00×
65,536	40.00 GiB	4.00 GiB	10.00×
131,072	80.00 GiB	8.00 GiB	10.00×