robss2020/microllm-lab

Private local model studio, AI chat, and agent workspace powered by WebGPU and WebLLM.

Run local AI models privately with GPU acceleration. Modern UI, HuggingFace integration. Built with Tauri + React + Rust.

High-performance In-browser LLM Inference Engine

Easily run LLMs locally using llama.cpp directly, without overhead.

A friendly GUI for running local LLMs with vLLM and llama.cpp — hardware-aware traffic-light guidance for every setting. Built on ideas from vllm-cli (Chen-zexi).

High-speed Large Language Model Serving for Local Deployment

A no-install needed GUI for Ollama and other local LLM providers.

Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser