Demo
NVIDIA ChatRTX
Your Personalized AI Chatbot
Version 0.5
What Is ChatRTX?
ChatRTX is a demo app that lets you personalize a GPT large language model (LLM) connected to your own content—docs, notes, images, or other data. Leveraging retrieval-augmented generation (RAG), TensorRT™-LLM, NVIDIA NIM™ microservices, and RTX™ acceleration, you can query a custom chatbot to quickly get contextually relevant answers. And because it all runs locally on your Windows RTX PC or workstation, you’ll get fast and private results.
Chat With Your Files
ChatRTX supports various file formats, including TXT, PDF, DOC/DOCX, JPG, PNG, GIF, and XML. Simply point the application at the folder containing your files, and it’ll load them into the library in a matter of seconds.
Talk to ChatRTX
ChatRTX features an automatic speech recognition system that uses AI to process spoken language and provide text responses with support for multiple languages. Simply click the microphone icon and talk to ChatRTX to get started.
Photo and Image Search
Let ChatRTX do the work—sort through your photo albums with a simple text or voice search, keeping everything private and hassle-free.
Making AI NIMble
ChatRTX provides access to NVIDIA NIM microservices, featuring the latest AI models optimized for RTX. With NVIDIA NIM, you can easily download, set up, and build AI-powered applications to accelerate workflows, boost productivity, and unlock the full potential of AI models.
See It in Action
Introducing ChatRTX
ChatRTX Update: Voice, Image, and new Model Support
Download NVIDIA ChatRTX
Simply download, install, and start chatting right away.
System Requirements
| Platform | Windows |
| GPU | NVIDIA® GeForce® RTX 5090 or 5080 GPU or NVIDIA® GeForce® RTX 30 or 40 Series GPU with at least 8GB of VRAM |
| RAM | 16GB or greater |
| OS | Windows 11 |
| Driver | 572.16 or higher |
| Disk Space | 70GB free disk space. *Installer size: 13MB; disk space requirements vary based on system configuration and installed models. See User Guide for details. |
Chat for Developers
The ChatRTX tech demo is built from the TensorRT-LLM RAG developer reference project available from GitHub. Developers can use that reference to develop and deploy their own RAG-based applications for RTX, accelerated by TensorRT-LLM.
NVIDIA NIM Microservices and Blueprints
AI, Ready for You
Harness the latest generative AI models locally on your RTX AI PC with NVIDIA NIM microservices and AI Blueprints. Optimized for your RTX GPU, NIM microservices unlock access to cutting-edge AI from your favorite apps—like ChatRTX, AnythingLLM, ComfyUI, and LM Studio. Combine them with Blueprints to quickly set up, customize, and deploy AI-driven workflows that automate tasks and unlock new capabilities. Shape and experience the AI of tomorrow, today. Powered by NVIDIA RTX™
NVIDIA Powers the World’s AI. And Yours.
Upgrade to advanced AI with NVIDIA GeForce RTX™ GPUs and accelerate gaming, creating, productivity, and development. Thanks to specialized built-in AI processors, you get world-leading AI technology and performance powering everything you do—plus, your data always stays local on your Windows PC.
Explore NVIDIA’s generative AI developer tools and enterprise solutions.