Hacker News new | ask | show | jobs
by texuf 811 days ago
Any recommendations for the latest and greatest way to run these locally?
5 comments

I am the author of Msty [1]. My goal is to make it as straightforward as possible with just one click (once you download the app). If you end up trying it, I would love to hear your feedback.

1: https://msty.app

I use a tool called LM Studio, makes it trivial to run these models on a Mac. You can also use it as a local API so it kinda acts like a drop-in replacement for the openAI API.
This looks amazing, but the docs mention .llamafiles exceed the Windows executable size limit, and there are workarounds to externalize the weights. Do you think this is an impediment to its becoming popular? Or is MS consumer hardware just far enough behind (w/o dedi gpu) that “there’s time”?
ollama
llamafile as per TFA...