PluelyPluelyDocs

Models · RadixArk

Pluely × RadixArk: DaisyRose 27B

Text → TextNo setup · no API key

DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from [Qwen3.8 27B](https://openrouter.ai/qwen/qwen3.8-27b) using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation. It is...

How RadixArk: DaisyRose 27B works in Pluely

Related models