The first launch of DaisyRose-27B.

DaisyRose-27B
Launching todayThe SGLang team's first open model, RL-trained for agents
Meet the team
Hunted by Ilyas. The makers are not on 25launches yet.

The SGLang team's first open model, RL-trained for agents
0 followers
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.
The first launch of DaisyRose-27B.

The SGLang team's first open model, RL-trained for agents
Hunted by Ilyas. The makers are not on 25launches yet.