Hacker news

  • Top
  • New
  • Past
  • Ask
  • Show
  • Jobs

DaisyRose-27B (https://www.radixark.com)

249 points by de_sty 1 day ago | 108 comments | View on ycombinator

chriddyp 1 day ago |

Very excited to see more post-training happening on these open models. Looking forward to trying this one out once it makes its way onto OpenRouter.

Qwen 27B really punches above its weight. 27B is small enough to fit on a Mac Mini / Macbook Pro which is very exciting.

Starting to see more promising examples of companies post-training. From my evals [1], I've tested 3 so far:

1. Fireworks' Ember-1 (postrained on Kimi K3, improved score by 10% in my evals)

2. Particle AI's Particle-1 (fine-tuned on DeepSeek V4.1 Flash, also a 10% improvement and a bit cheaper and faster)

3. Nex AGI's Nex-N2.6 (post-trained on GLM 5.3 Flash. Didn't show an improvement in my eval, and had a couple runaway loops that made it expensive).

With Thinking Machines' western open model release (Inkling Small) a few weeks ago, I expect we'll see more of this, especially out of western companies.

[1] https://plotly.com/blog/nex-n2-6-plotly-data-analytics-bench...

woah 1 day ago |

The heavy reliance on eval datasets showcased here and also evidenced by the frontier lab's high payments for such data cast doubt on the claims that AI will become self-improving soon

pkoiralap 1 day ago |

Sabi-noema also looks like a close competitor in the same space. Built from qwen3.8 and made better.

https://huggingface.co/sabicap/sabi-noema

Also HF model here: https://huggingface.co/RadixArk/DaisyRose-27B

jacquesm 1 day ago |

I always wonder what you lose when you start maxing out some specific benchmark. It is really hard to do this in a balanced way and I would love if everybody that did these kind of efforts would take the time to also list the before/afters of a number of other benchmarks that they did not use in their training.

xlayn 1 day ago |

Snap, no gguf to download, will wait for one to appear to test, any improvement over an already good model is good news.

"18 days on 144 H200 GPUs" insane.. didn't thought so much hardware would be needed to train Qwen.

mips_avatar 1 day ago |

How did you guys set up the RL topology? Were you guys doing individual RL nodes (4xh200 rollout/4xh200 train) or did you have dedicated trainer and rollout nodes?

potus_kushner about 15 hours ago |

where's the 35b-a3b variant they mention to have also trained? much more interesting for consumer hw. and they should've started with ornith 1.5, not qwen 3.6. we don't need 10 models that's each about 10-20% better than qwen 3.6 - we need a model that accumulates the gains.

octoberfranklin 1 day ago |

FWIW that is about $331,000 on low-onboarding-grief clouds (e.g. vast.ai) right now using the SXM variants they used.

You might be able to shave that down using a different flavor of H200 (like PCIe) but it would take more hours, so benefits are unclear.

undefined 1 day ago |

undefined

0x69420 1 day ago |

3.8 27B is an interesting choice. on the face of it, doing RL on it feels like refrying twice-cooked pork then stuffing it in the microwave for good measure. the fact that even one benchmark (tb4.1) increased more than marginally is kind of miraculous. would be interesting to see where "miles" would take eg. 3.8 flash next, which is already impressive despite being an under-trained architectural preview.

robertkarl 1 day ago |

I look forward to testing this against my private eval set to determine if it's benchmaxxing or actual improvement based on just 1200 tasks. downloading it now

XCSme 1 day ago |

Is it post-training or bench-maxxing?

htrp about 18 hours ago |

still can't sign up for radixark to try this model

DeathArrow about 23 hours ago |

One pet project of mine would be - if I had the resources, of course - to get a simple but decent model and post train it intensely for just one language and one task.

For example doing backend projects using C# or Go.

DeathArrow 1 day ago |

Since some talented people with more modest means were able to do such a job, I wonder why Alibaba didn't do something like this when they trained the model.

They left a lot of performance on the table.

Which makes me wonder if such kind of optimizations are possible for other models like Deepseek v4.1 Flash 1017.

amarinhodev 1 day ago |

[flagged]

SparkleQwen27b about 21 hours ago |

[flagged]

bzvox 1 day ago |

[dead]