8 projects
kooka-server
local inference web server for MLX / mlx-lm.
mlx-voxtral
Voxtral audio processing and model implementation for Apple Silicon using MLX
mlx_hubert
HuBERT (Hidden Unit BERT) implementation in MLX for Apple Silicon
files-to-chat
`files-to-chat` is a command-line tool designed to process files or folders, converting their contents into a format suitable for use as a prompt context to chat with large language models (LLMs).
mlx-sharding
A package for MLX model sharding and distributed inference
mlx-nougat
A CLI tool for OCR using the Nougat model
mlx-llm-server
server to serve mlx model as an OpenAI compatible API
mlx-moe
A tool to generate text with mlx-moe model.
