RadixArk releases its first model, DaisyRose-27B
Understand this story
RadixArk releases its first model, DaisyRose-27B, built on Qwen3.8-27B with reinforcement learning post-training using Miles. The company says it trained for 18 days on 144 H200 GPUs using only 1,200 curated tasks, raising Terminal Bench 4.1 pass@1 from 5.6% to 12.0%. Checkpoints are available under the Apache 2.0 license in BF16, FP8 and NVFP4 formats; RadixArk recommends deploying with SGLang and DSpark speculative decoding.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hugging Face BlogFeaturedDaisyRose-27B: Pushing the Frontier of Post-Training Efficiency
RadixArk released DaisyRose-27B, its first model, built on Qwen3.8-27B and trained with reinforcement learning using Miles on long-horizon agent tasks with sessions up to 1M tokens, using 1,200 curated tasks over 18 days on 144 H200 GPUs. It raises Terminal-Bench 4.1 pass@1 from 5.6% to 12.0% and improves on every listed benchmark, with checkpoints available under Apache 2.0 in BF16, FP8 and NVFP4. The model keeps Qwen3.8-27B's architecture, tokenizer, chat template, image understanding and 256K-token context window.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 19 05:00
- Change in the past 24 hours
- -51%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.