NVIDIA Unveils RTX AI PCs with Accelerated Generative AI Models
At CES, NVIDIA made a groundbreaking announcement regarding the launch of foundation models that run locally on NVIDIA RTX AI PCs. These models, offered as NVIDIA NIM microservices, are powered by the new GeForce RTX 50 Series GPUs, which boast up to 3,352 trillion operations per second of AI performance and 32GB of VRAM. The GPUs are built on the NVIDIA Blackwell architecture and are the first consumer GPUs to support FP4 compute, enhancing AI inference performance by 2x and enabling generative AI models to run locally with a smaller memory footprint compared to previous hardware.
GeForce has always been a crucial platform for AI developers, with the first GPU-accelerated deep learning network, AlexNet, being trained on a GeForce GTX 580 in 2012. Over 30% of published AI research papers last year cited the use of GeForce RTX. With the introduction of generative AI and RTX AI PCs, NVIDIA is democratizing AI development, allowing anyone to become a developer. Low-code and no-code tools like AnythingLLM, ComfyUI, Langflow, and LM Studio provide enthusiasts with simple graphical user interfaces to use AI models in complex workflows.
NVIDIA is set to release a pipeline of NIM microservices for RTX AI PCs from top model developers such as Black Forest Labs, Meta, Mistral, and Stability AI. These microservices cover a wide range of use cases including large language models, vision language models, image generation, speech, retrieval-augmented generation (RAG), PDF extraction, and computer vision. By offering NIM microservices, NVIDIA is making it easier for users to access and deploy the latest generative AI models.
Join our mission to the .MOON! 
Additionally, NVIDIA announced the Llama Nemotron family of open models designed for agentic tasks. The Llama Nemotron Nano model, offered as a NIM microservice for RTX AI PCs, excels at tasks like instruction following, function calling, chat, coding, and math. NIM microservices are optimized for deployment across NVIDIA GPUs, whether in RTX PCs and workstations or in the cloud.
Developers and enthusiasts will be able to download and run these NIM microservices on Windows 11 PCs with Windows Subsystem for Linux (WSL). NVIDIA has also partnered with top AI development and agent frameworks to ensure compatibility with NIM microservices, enabling users to deploy AI models seamlessly across different platforms.
To showcase the capabilities of NIM microservices, NVIDIA previewed Project R2X, a vision-enabled PC avatar that can assist users with various tasks. The avatar is rendered using NVIDIA RTX Neural Faces and animated with the new diffusion-based NVIDIA Audio2Face-3D model. It can be connected to cloud AI services like OpenAI’s GPT4o and xAI’s Grok, as well as NIM microservices and AI Blueprints.
NVIDIA AI Blueprints, which include reference AI workflows that can run locally on RTX PCs, will be available starting in February. These blueprints enable developers to create podcasts from PDF documents, generate images guided by 3D scenes, and more. NIM-ready RTX AI PCs will be offered by leading PC manufacturers and system builders.
In conclusion, NVIDIA’s new RTX AI PCs, powered by GeForce RTX 50 Series GPUs and NIM microservices, are set to revolutionize generative AI development. With a focus on accessibility and performance, NVIDIA is paving the way for AI enthusiasts and developers to explore the possibilities of AI technology.