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

Other models of this size have done well in the past.

Qwen2.5 coder, for example, can correctly answer the question at 7B.

Deepseek R1 was also capable of giving a correct response.

It's obviously a doable. Such a model locally is useful in autocomplete while programming.

 help



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

Search: