RadixArk/DaisyRose-27B
image-text-to-text · ♥ 292 · ↓ 1.8K
- Taskimage-text-to-text
- Downloads1375
- Likes284
- Licenseapache-2.0
image-text-to-text · ♥ 292 · ↓ 1.8K
DaisyRose-27B is RadixArk's first model: a multimodal reasoning model built on Qwen3.8-27B with reinforcement learning only, without any supervised fine-tuning or distillation. It was trained on about 1,200 curated long-horizon agent tasks, with sessions of up to 1M tokens, for 18 days on 144 H200 GPUs. Terminal Bench 4.1 pass@1 rises from 5.6 to 12.0, and the model also improves on most of the other coding,…
DaisyRose-27B keeps the base model's architecture, tokenizer and chat template, along with its image understanding and 256K-token context, so it is a drop-in replacement for Qwen3.8-27B in existing inference and post-training stacks. Weights are released under Apache-2.0 in BF16, FP8, and NVFP4.
Excerpt from the model card on Hugging Face ↗.
RadixArk/DaisyRose-27B was first seen on Hugging Face · Trending models on Nov 19, 2026. Since then it has appeared in 73 checks on 4 different days. Its best position was #12 of 30, reached on Nov 21, 08:45 UTC. It is #21 right now, slipping from #20 to #21 over the last 6 checks.
Position on Hugging Face · Trending models at every check (lower is better).
Best rank per day (UTC).
🔥 as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 22, 16:45 UTC it is #21, slipping from #20 to #21 over the last 6 checks.
#12 on Hugging Face · Trending models, on Nov 21, 08:45 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 19, 2026 and has been on the list on 4 days (73 checks) since.
It is tagged image-text-to-text with transformers on Hugging Face and has 1375 downloads under the apache-2.0 license.