Tags: #local-inference

An open-source AI engine enabling local execution of various AI models (LLMs, vision, voice, image, video) on diverse hardware, including CPU-only setups.

llama-swap enables seamless hot-swapping and management of multiple local generative AI models, acting as a unified API gateway compatible with OpenAI and Anthropic standards.

Diffusion Bee provides the easiest one-click solution to run Stable Diffusion locally on Intel and M-series Macs, enabling AI art generation without technical knowledge or cloud dependencies.

A fast, local neural text-to-speech system for generating high-quality speech offline.

A C#/.NET library for efficient local execution of Large Language Models (LLMs) like LLaMA and LLAVA, leveraging llama.cpp.