RadixArk releases DaisyRose-27B after reinforcement learning on long-horizon agent tasks
RadixArk has released DaisyRose-27B, a Qwen3.8-27B derivative trained with reinforcement learning on about 1,200 curated agent tasks. The developer says it trained for 18 days on 144 H200 GPUs and retains the base model's 256K-token context and image understanding. The release's benchmark comparisons need qualification: a prominent Terminal …
SourcesHugging Face Blog
Read development