Looking into running models locally, maybe a 405B parameter model sounds like th... | Hacker News

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

		j45 on Dec 6, 2024 \| parent \| context \| favorite \| on: ChatGPT Pro Looking into running models locally, maybe a 405B parameter model sounds like the place to start. Once understood you could practice with a private hosted llm (run your own model) to tweak and get it dialled in per hour, and then make the leap.

wkat4242 on Dec 8, 2024 [–]

And now you can get the 405b quality in a 70b according to meta. Costs really come down massively with that. I wonder if it's really as good as they say though.

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