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.
Summary
Shoehorn is a tool that allows users to quantize machine learning models for local use on Mac, Linux, and Windows, featuring an intuitive GUI for easy setup. The project shows promising results and is detailed in its GitHub documentation, making it a practical resource for developers looking to optimize model performance.
Comments (16 of ) ⌛