Is Qwen3.6-27B or Le-Chaton-Slim-23B smaller?

Le-Chaton-Slim-23B is smaller at Q4_K_M: 13.21 GiB against 15.41 GiB.

Which uses less memory at long context?

Qwen3.6-27B — its KV cache at 32K context is 1.6x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-27B vs Le-Chaton-Slim-23B

At Q4_K_M, Le-Chaton-Slim-23B is the smaller download — 14,183,211,648 bytes against 16,547,397,888. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 1.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-27B	Le-Chaton-Slim-23B
Parameters	27.8B	23.3B
Architecture	qwen35	llama
Layers	64	26
Native context	262,144	262,144
Mixture of experts	no	yes, 10 experts
Quantizations published	40	34
Smallest quantization	8.74 GiB	4.59 GiB
Q4_K_M	15.41 GiB	13.21 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-27B	Le-Chaton-Slim-23B	Ratio
4,096	0.25 GiB	0.41 GiB	1.62×
8,192	0.50 GiB	0.81 GiB	1.62×
16,384	1.00 GiB	1.63 GiB	1.62×
32,768	2.00 GiB	3.25 GiB	1.62×
65,536	4.00 GiB	6.50 GiB	1.62×
131,072	8.00 GiB	13.00 GiB	1.62×