A high-performance inference engine built in Rust, supporting models like Qwen 3.8 27b and Flash next. It achieves high token per second rates for LLM serving.
Generative AI Voice & Image UI Generator — A full-stack app that turns text prompts and images into responsive UI code using local AI models with Ollama, CodeLLaMA, and LLaVA. Runs 100% locally with no cloud APIs, featuring an Express backend and a simple HTML/JS/Tailwind frontend for live preview.