RadixArk releases DaisyRose-27B, an open agent model built on Qwen3.8-27B
RadixArk has released DaisyRose-27B, its first model, post-trained from Qwen3.8-27B with reinforcement learning on long-horizon agent tasks. Checkpoints are published under Apache 2.0 in BF16, FP8 and NVFP4, and the model keeps the base model's 256K-token context window and image understanding. On Terminal-Bench 4.1, pass@1 rose from 5.6% to 12.0%, and RadixArk reports smaller gains on other coding, reasoning and instruction-following benchmarks. The team recommends serving it with SGLang.
Why it matters
An openly licensed agent model that keeps a 256K context window gives teams a self-hostable option for long-running terminal and coding agents, with published benchmark comparisons against the base model it was trained from.
Sources
- PrimaryHugging Face
Written by AIToolMaps from the source above and checked against it sentence by sentence.