turboquant-mlx

Extreme weight + KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant)

What is turboquant-mlx?

Extreme weight + KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant)

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/manjunathshivaturboquant-mlx.svg)](https://yunodb.com/tools/manjunathshivaturboquant-mlx?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/manjunathshivaturboquant-mlx?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/manjunathshivaturboquant-mlx.svg" alt="Featured on YunoDB" height="20"></a>