Model comparison

WorldSim-Opus-3.6-35B-A3B vs Qwen3.6-35B-A3B

At Q4_K_M, Qwen3.6-35B-A3B is the smaller download — 21,166,757,728 bytes against 21,391,448,992.

From the file· summed bytes, KV per layer

Side by side

WorldSim-Opus-3.6-35B-A3BQwen3.6-35B-A3B
Parameters35.1B36.0B
Architectureqwen35moeqwen35moe
Layers4040
Native context262,144262,144
Mixture of expertsyes, 256 expertsyes, 256 experts
Quantizations published4961
Smallest quantization6.97 GiB8.77 GiB
Q4_K_M19.92 GiB19.71 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextWorldSim-Opus-3.6-35B-A3BQwen3.6-35B-A3BRatio
4,0960.08 GiB0.08 GiB1.00×
8,1920.16 GiB0.16 GiB1.00×
16,3840.31 GiB0.31 GiB1.00×
32,7680.63 GiB0.63 GiB1.00×
65,5361.25 GiB1.25 GiB1.00×
131,0722.50 GiB2.50 GiB1.00×