N
Hacker Next
new
past
show
ask
show
jobs
submit
login
▲
Show HN: Shoehorn – Quantize any model down to run on your machine
(
notactuallytreyanastasio.github.io
)
15 points by
rhgraysonii
2 hours ago
|
2 comments
add comment
Rendered at 16:46:07 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
hmokiguess 57 minutes ago
[-]
Reminds me of
https://github.com/AlexsJones/llmfit
mbuchel-hn 1 hours ago
[-]
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?