NVIDIA Launches Chat With RTX, An AI Chat Bot For RTX 30 & 40 Series GPUs

NVIDIA like many other companies have their sights aimed upon AI as the next big profit margin and today they have introduced a new AI chat bot. Now I know what you’re thinking, Not another one, but this one is a bit different as it will be exclusive for RTX 30 and 40 series GPUs and will work as a localised system.

Chat With RTX

NVIDIA has revealed Chat With RTX , a new demo app which lets you personalize a GPT large language model connected to your own content be it docs, notes, videos or other data. Using Retrieval-augmented generation, TensorRT LLM and RTX acceleration, you can query a custom chatbot to quickly get contextually relevant answers all running locally on your own computer rather than through the cloud.

The process of using Chat with RTX will involve creating a dataset within your PC and then connect it to a large language model that exists. If you’ve used chatGPT it should all be very familiar to you.

What NVIDIA Had To Say

“Generative AI is the single most significant platform transition in computing history and will transform every industry, including gaming,” said Jensen Huang, founder and CEO of NVIDIA. “With over 100 million RTX AI PCs and workstations, NVIDIA is a massive installed base for developers and gamers to enjoy the magic of generative AI.”

I haven’t tinkered too much with AI, I’ve yet to find a purpose that suits my needs. I imagine I’ll find something as it develops and once all of the marketing band wagoning is ironed out, looking at you hardware manufacturers with your “AI chips” and “AI fan profiles”.

Chat with RTX can be downloaded at nvidia.com and requires a 30 or 40 series GPU or NVIDIA RTX Amper or Ada generation GPU with at least 8GB of VRAM. The OS requirement states Windows 11 but it may work fine on 10 as well.