NVIDIA Blackwell GeForce RTX 50 Series Opens New World of AI Computer Graphics

NVIDIA today introduced the most advanced consumer GPUs for gamers, creators, and developers—the GeForce RTX 50 Series GPUs for desktops and laptops. Based on NVIDIA Blackwell architecture, fifth-generation Tensor Cores and fourth-generation RT Cores, the GeForce RTX 50 series delivers breakthroughs in AI-powered rendering, including neural shaders, digital human technology, geometry and lighting.

“Blackwell, the engine of artificial intelligence, is now available to gamers, developers and creatives,” said Jensen Huang, founder and CEO of NVIDIA. “By combining AI-powered neural rendering and ray tracing, Blackwell is the most significant innovation in computer graphics since we introduced programmable shading 25 years ago.” The GeForce RTX 5090 GPU, the fastest GeForce RTX GPU to date, contains 92 billion transistors, delivering more than 3,352 trillion operations per second (TOPS) of processing power. Innovations in Blackwell architecture and DLSS 4 mean the GeForce RTX 5090 GPU is up to 2x faster than the GeForce RTX 4090 GPU.

GeForce Blackwell comes on laptops with all the features of desktop models, providing a significant upgrade to laptop computing, including exceptional graphics capabilities and outstanding efficiency. The Blackwell generation with NVIDIA Max-Q technology extends battery life by up to 40% and features thin and light laptops that retain their sleek design without sacrificing power and performance.

NVIDIA DLSS 4 improves performance up to 8 times
DLSS 4 debuts multi-frame generation, which improves frame rates by using artificial intelligence to generate up to three frames for every frame rendered. It works in unison with the DLSS suite of technologies to increase performance up to 8 times over traditional rendering while maintaining responsiveness thanks to NVIDIA Reflex technology.

DLSS 4 also introduces the graphics industry’s first real-time transformer model architecture application. DLSS ray reconstruction and transformer-based super-resolution models use 2x more parameters and 4x more computation, resulting in greater stability, reduced ghosting, higher detail, and improved anti-aliasing in game scenes. On launch day, DLSS 4 will be supported on GeForce RTX 50 series GPUs in more than 75 games and applications.

NVIDIA Reflex 2 introduces Frame Warp, an innovative technology that reduces latency in games by updating the rendered frame based on the last mouse input just before it is sent to the display. Reflex 2 can reduce latency by up to 75%. This gives gamers a competitive edge in multiplayer games and makes single-player games more responsive.

Blackwell brings artificial intelligence to shaders
Twenty-five years ago, NVIDIA introduced GeForce 3 and programmable shaders, which laid the foundation for two decades of graphics innovation, from pixel shading to computational shading and real-time ray tracing. Along with the GeForce RTX 50 series GPUs, NVIDIA is introducing RTX Neural Shaders, which combine small AI networks with programmable shaders to unlock cinema-quality footage, lighting, and more in real-time gaming.

Rendering game characters is one of the most challenging tasks in real-time graphics, as humans tend to notice minute errors or artifacts in digital humans. RTX Neural Faces takes a simple rasterized face and 3D pose data as input and uses generative AI to render a time-stable, high-quality digital face in real time.

RTX Neural Faces is complemented by new RTX technologies for hair and skin tracing. Along with the new RTX Mega Geometry technology, which allows for 100x more ray-traced triangles in a scene, these enhancements are designed to provide a huge leap in the realism of game characters and environments.

Neural rendering capabilities, DLSS 4, and the new DLSS Transformer model are showcased on GeForce RTX 50 series GPUs with Zorah, a groundbreaking demonstration of new technology from NVIDIA.

Standalone game characters
GeForce RTX 50 series GPUs feature advanced AI TOPS technologies to control autonomous game characters in parallel with game rendering.

NVIDIA is introducing a suite of new NVIDIA ACE technologies that enable game characters to perceive, plan, and act like human players. ACE-based standalone characters are being integrated into KRAFTON’s PUBG: BATTLEGROUNDS and InZOI, the publisher’s upcoming life simulation game, as well as Wemade Next’s MIR5.

In PUBG, teammates powered by NVIDIA ACE plan and execute strategic actions, working dynamically with human players to ensure survival. InZOI features Smart Zoi characters that autonomously adjust behavior depending on life goals and in-game events. In MIR5, raid bosses, driven by the Large Language Model (LLM), adapt tactics based on player behavior, creating more dynamic and challenging encounters.

AI Foundation Models for PC RTX AI
Showcasing how RTX enthusiasts and developers can use NVIDIA NIM microservices to build AI agents and assistants, NVIDIA will release a suite of NIM microservices and AI Blueprints for RTX AI machines from leading modelers such as Black Forest Labs, Meta, Mistral and Stability AI.

Use cases include LLM, vision language models, image generation, speech, model embedding for search-enabled generation, PDF extraction, and computer vision. NIM microservices include all the necessary components to run AI on PCs and are optimized for deployment on all NVIDIA GPUs.

To demonstrate how enthusiasts and developers can use NIM to create artificial intelligence agents and assistants, NVIDIA today introduced Project R2X, a computer vision-enabled computer avatar that can put information at the user’s fingertips, assist with desktop applications and video conferencing calls, read and summarize documents. and much more.

AI-powered tools for authors
GeForce RTX 50 Series GPUs accelerate creativity. RTX 50 Series GPUs are the first consumer GPUs to support FP4 precision, delivering 2x faster AI imaging performance for models like FLUX and allowing generative AI models to run locally with less memory than previous hardware generations.

The NVIDIA Broadcast app has two beta AI-powered features for streamers: Studio Voice, which improves microphone audio, and Virtual Key Light, which illuminates faces for better streams. Streamlabs introduces an intelligent streaming assistant powered by NVIDIA ACE and Inworld AI that acts as a co-host, producer and technical assistant to enhance the quality of live events.

Availability
For desktop users, the GeForce RTX 5090 GPU with 3,352 AI TOPS and the GeForce RTX 5080 GPU with 1,801 AI TOPS will be available on January 30 for $1,999 and $999, respectively.

The GeForce RTX 5070 Ti with 1,406 AI TOPS and GeForce RTX 5070 with 988 AI TOPS will be available starting in February for $749 and $549, respectively.

GeForce RTX 5090, RTX 5080 and RTX 5070 NVIDIA Founders Edition GPUs will be available directly from NVIDIA and select retailers worldwide.