Get the latest tech news

Show HN: Shoehorn – Quantize any model down to run on your machine


Solves a per-tensor quantization that uses 99.99% of your exact VRAM budget — every spare megabyte spent where it buys the most quality. macOS, Linux, and Windows.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of model

model

Photo of machine

machine

Photo of Shoehorn

Shoehorn

Related news:

News photo

Baking a Model: A Metaphor for LLM Training

News photo

‘I feel like I’m at war’: are we losing the battle against machine-made music | Despite outcry from musicians, AI slop is creeping into the charts as record labels scramble to adapt to a new normal where hits can be made at the click of a button

News photo

If I own Claude's outputs why can't I train my own model on them?