Model comparison

Le-Chaton-Slim-23B vs Qwen3-Coder-30B-A3B-Instruct

At Q4_K_M, Le-Chaton-Slim-23B is the smaller download — 14,183,211,648 bytes against 18,556,689,568.

From the file· summed bytes, KV per layer

Side by side

Le-Chaton-Slim-23BQwen3-Coder-30B-A3B-Instruct
Parameters23.3B30.5B
Architecturellamaqwen3moe
Layers2648
Native context262,144262,144
Mixture of expertsyes, 10 expertsyes, 128 experts
Quantizations published3446
Smallest quantization4.59 GiB7.46 GiB
Q4_K_M13.21 GiB17.28 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextLe-Chaton-Slim-23BQwen3-Coder-30B-A3B-InstructRatio
4,0960.41 GiB0.38 GiB1.08×
8,1920.81 GiB0.75 GiB1.08×
16,3841.63 GiB1.50 GiB1.08×
32,7683.25 GiB3.00 GiB1.08×
65,5366.50 GiB6.00 GiB1.08×
131,07213.00 GiB12.00 GiB1.08×