NVIDIA Launches RTX, Personalized GPT Models

ODSC - Open Data Science
2 min readFeb 22, 2024

Interested in creating your own GPT LLM model based on your own files? Imagine one that learns from your docs, videos, notes, and other pieces of data! Well, NVIDIA is ready to make this a reality with RTX.

Leveraging TensorTR-LLM, RTX, and retrieval-augmented generation, users are able to personalize a chatbot that answers their questions and fulfills creative demands. Currently, RTX is a free tech demo from NVIDIA. In all, the app is tailored to your specific needs, running it directly on your RTX-powered Windows PC.

Now, what do you need to run RTX on your own system? Well, the system requirements are modest. According to the announcement, users need an RTX 2080 Ti or better graphics card, 32GB of RAM, and 10GB of free disk space.

As you can see, not too bad and pretty much in reach for most users. So once set up, feed Chat with RTX your own text, code, or image files to train your unique LLM. The more data you provide, the sharper its responses become.

Now wait for a moment, and imagine a chatbot that seamlessly translates languages, crafts poems on demand, or even answers your technical questions with expert-level insight based on the data you feed it.

RTX makes this a reality for users who are adventurous enough to take on the challenge. This technology leverages “retrieval-augmented generation,” allowing your LLM to access and process your personal data alongside vast online information sources.

While still in its demo phase, Chat with RTX opens exciting possibilities for developers and curious minds alike. Imagine creating personalized assistants for specific tasks, crafting chatbots for businesses, or simply having a unique AI companion at your fingertips. The potential is vast.

For those who many not be well versed in AI, this could be an interesting means of learning what it takes to becoming a AI architect. Now if you’re interested, just head over to NVIDIA’s website and download Chat with RTX today.

Keep in mind, according to NVIDIA, the more you interact and engage, the smarter and more personal your custom LLM becomes.

Originally posted on OpenDataScience.com

Read more data science articles on OpenDataScience.com, including tutorials and guides from beginner to advanced levels! Subscribe to our weekly newsletter here and receive the latest news every Thursday. You can also get data science training on-demand wherever you are with our Ai+ Training platform. Interested in attending an ODSC event? Learn more about our upcoming events here.



ODSC - Open Data Science

Our passion is bringing thousands of the best and brightest data scientists together under one roof for an incredible learning and networking experience.