25launches

DaisyRose-27B

The SGLang team's first open model, RL-trained for agents

0 followers

Visit huggingface.co (opens in a new tab)

Artificial IntelligenceOpen SourceDeveloper Tools

DaisyRose-27B is the first model from RadixArk, the team behind the SGLang inference engine. It is Qwen3.8-27B trained further with reinforcement learning only, on about 1,200 long agent tasks in coding, ML and science. RadixArk reports Terminal Bench 4.1 going from 5.6 to 12.0, with smaller gains on its other coding and reasoning tests. It keeps the base model's image input and 256K context and runs on a single GPU. BF16, FP8 and NVFP4 weights, Apache-2.0.