NVIDIA is making generative AI accessible to everyday PC users by equipping 100 million existing RTX graphics cards with new tools and accelerated software that let people run AI models locally, without sending data to the cloud. The company announced a suite of new GeForce RTX SUPER desktop GPUs, AI laptops from major manufacturers, and developer-friendly software designed to bring text-to-image generation, large language models (LLMs), and AI-powered creative tools directly to consumer and professional machines.

The shift reflects a fundamental change in how AI is being deployed. Rather than relying on cloud services, running generative AI locally on a PC offers critical advantages: better privacy since data stays on your device, lower latency because there is no network delay, and reduced costs by eliminating per-use cloud fees. NVIDIA is betting that its massive installed base of RTX GPUs makes PCs the ideal platform for this transition.

What New Hardware Is NVIDIA Releasing for AI on PCs?

NVIDIA announced three new GeForce RTX 40 SUPER Series graphics cards designed to accelerate generative AI workloads. The flagship GeForce RTX 4080 SUPER generates AI video 1.5 times faster and images 1.7 times faster than the previous-generation RTX 3080 Ti. All SUPER GPUs feature Tensor Cores, specialized processing units that deliver up to 836 trillion operations per second, enabling transformative AI capabilities for gaming, content creation, and productivity.

Beyond desktop cards, every major PC manufacturer is releasing new RTX AI laptops this month. These systems include Acer, ASUS, Dell, HP, Lenovo, MSI, Razer, and Samsung models that deliver a performance increase ranging from 20 times to 60 times compared with using neural processing units (NPUs), the AI chips built into some mobile processors. Mobile workstations with RTX GPUs can also run NVIDIA AI Enterprise software, including TensorRT and NVIDIA RAPIDS, for simplified, secure generative AI and data science development.

How to Build and Deploy AI Models on Your PC?

• Use AI Workbench: NVIDIA AI Workbench, available in beta later this month, offers streamlined access to popular model repositories like Hugging Face, GitHub, and NVIDIA NGC, with a simplified interface that lets developers easily reproduce, collaborate on, and migrate AI projects without deep technical expertise.
• Optimize with TensorRT-LLM: This open-source library accelerates and optimizes inference performance of large language models for PCs. The latest update adds support for Phi-2 and other pre-optimized models that run up to 5 times faster compared to other inference backends.
• Integrate with HP AI Studio: In collaboration with HP, NVIDIA is integrating AI Foundation Models and Endpoints into HP AI Studio, a centralized platform that allows users to easily search, import, and deploy optimized models across PCs and the cloud.

For developers who have already built AI models, NVIDIA TensorRT provides optimization tools that take full advantage of RTX GPUs' Tensor Cores. This means models run significantly faster on consumer hardware without sacrificing accuracy.

What New AI-Powered Applications Are Coming to PCs?

NVIDIA and its developer partners are releasing a wave of generative AI-powered applications and services designed to run on RTX PCs. These include RTX Remix, a platform for creating stunning remasters of classic games using generative AI tools that transform basic textures into modern, 4K-resolution, physically based rendering materials. The tool releases in beta later this month.

Text-to-image generation is also getting a major performance boost. NVIDIA TensorRT now accelerates Stable Diffusion XL (SDXL) Turbo and latent consistency models, improving performance by up to 60 percent compared with the previous fastest implementation. An updated Stable Diffusion WebUI TensorRT extension is also available, supporting SDXL, SDXL Turbo, and improved LoRA (Low-Rank Adaptation) support for fine-tuning models.

NVIDIA DLSS 3 with Frame Generation, an AI technology that increases frame rates up to 4 times compared with native rendering, will be featured in a dozen of 14 new RTX games announced, including Horizon Forbidden West, Pax Dei, and Dragon's Dogma 2. For conversational AI, Chat with RTX, an NVIDIA tech demo releasing later this month, allows users to interact with their own notes, documents, and other content using retrieval-augmented generation (RAG), a technique that connects local language models to personal data.

"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."

Jensen Huang, Founder and CEO at NVIDIA

NVIDIA's strategy reflects a broader industry recognition that the future of AI is not exclusively cloud-based. By equipping hundreds of millions of existing PCs with the software and tools needed to run generative AI locally, NVIDIA is positioning consumer and professional machines as primary platforms for AI creation and inference, reducing dependence on expensive cloud infrastructure and addressing privacy concerns that have become increasingly important to both individuals and enterprises.