I've had even better results using the dense 27B model -- less looping and churn... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		anana_ 26 days ago \| parent \| context \| favorite \| on: Something is afoot in the land of Qwen I've had even better results using the dense 27B model -- less looping and churning on problems

androiddrew 26 days ago [–]

Which dense model are you referring to? The dense model isn’t finetuned for code instruction according to the model card.

anana_ 26 days ago | [–]

https://huggingface.co/Qwen/Qwen3.5-27B

I wasn't aware of that, which page mentions that?

zerebos 26 days ago | | [–]

Yeah the page you linked even shows the benchmarks in coding for this model, so I'd be curious where that claim comes from

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact