Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Show HN: Shoehorn – Quantize any model down to run on your machine (notactuallytreyanastasio.github.io)
45 points by rhgraysonii 1 day ago | hide | past | favorite | 9 comments
Working on Mac, Linux, and Windows now. I include a simple GUI to find new models and get things built and set up. It is working quite well across a few models for me. The GitHub README and DESIGN.md files go into detail of the how/why and it's working remarkably well so far. https://github.com/notactuallytreyanastasio/shoehorn
 help



Reminds me of https://github.com/AlexsJones/llmfit

reply


LLMFit tells you what can run on something. I built something quite similar to their search into Shoehorn now.

reply


This is interesting. I wonder how it could work with something like https://github.com/JustVugg/colibri.

reply


does this work similar to airllm? i am wondering how it would handle something like quantizing kimi k3 on a budget of 8 gbs, or is that something you are not attempting to solve yet?

reply


Yes that is exactly what this does.

reply


Could you explain what happens when you try to shoehorn a 2.4T parameter model into a 24gb m4 mac?

reply


Wondering the same thing but for 48gb M5 Max.

reply


tried it out but based on the model sizing result i got i got an insufficient memory error when the server started running

reply


If you could post an issue if you still have the error around that would be awesome.

reply




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

Search: