DaisyRose 27B

radixark/daisyrose-27b
Confronta

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.

Rilasciato
21 nov 2026
Input
TextImage
Output
Text
Supporto
RagionamentoChiamata di strumentiOutput strutturati

Ultime notizie su DaisyRose 27B

Articoli recenti e post della community, con link alle fonti originali.