Is GLM-4.1V-9B-Thinking or Qwythos-9B-Claude-Mythos-5-1M smaller?

GLM-4.1V-9B-Thinking is smaller at Q4_K_M: 5.74 GiB against 10.73 GiB.

Which uses less memory at long context?

Qwythos-9B-Claude-Mythos-5-1M — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

GLM-4.1V-9B-Thinking vs Qwythos-9B-Claude-Mythos-5-1M

At Q4_K_M, GLM-4.1V-9B-Thinking is the smaller download — 6,166,574,432 bytes against 11,516,776,704. At long context the gap widens: Qwythos-9B-Claude-Mythos-5-1M's KV cache at 32K is 1.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	GLM-4.1V-9B-Thinking	Qwythos-9B-Claude-Mythos-5-1M
Parameters	10.3B	9.4B
Architecture	glm4	qwen35
Layers	40	32
Native context	65,536	1,048,576
Mixture of experts	no	no
Quantizations published	43	16
Smallest quantization	2.98 GiB	5.38 GiB
Q4_K_M	5.74 GiB	10.73 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	GLM-4.1V-9B-Thinking	Qwythos-9B-Claude-Mythos-5-1M	Ratio
4,096	0.16 GiB	0.13 GiB	1.25×
8,192	0.31 GiB	0.25 GiB	1.25×
16,384	0.63 GiB	0.50 GiB	1.25×
32,768	1.25 GiB	1.00 GiB	1.25×
65,536	2.50 GiB	2.00 GiB	1.25×
131,072	5.00 GiB	4.00 GiB	1.25×