LAS VEGAS, Jan. 06, 2025 (GLOBE NEWSWIRE) — CES — NVIDIA has announced the most sophisticated consumer GPUs for gamers, creators, and developers — the GeForce RTX™ 50 Series Desktop and Laptop GPUs.
Utilizing the NVIDIA Blackwell architecture, fifth-generation Tensor Cores, and fourth-generation RT Cores, the GeForce RTX 50 Series achieves advancements in AI-enhanced rendering, encompassing neural shaders, digital human technologies, geometry, and lighting.
“Blackwell, the driving force of AI, has arrived for PC gamers, developers, and creators,” stated Jensen Huang, founder and CEO of NVIDIA. “Integrating AI-driven neural rendering and ray tracing, Blackwell represents the most crucial innovation in computer graphics since the advent of programmable shading 25 years ago.”
The GeForce RTX 5090 GPU — the quickest GeForce RTX GPU thus far — boasts 92 billion transistors, offering more than 3,352 trillion AI operations per second (TOPS) of computational power. Innovations in Blackwell architecture and DLSS 4 enable the GeForce RTX 5090 GPU to outperform the GeForce RTX 4090 GPU by as much as 2x.
GeForce Blackwell also caters to laptops, incorporating all the capabilities of desktop versions, resulting in a substantial upgrade to portable computing, featuring remarkable graphics performance and efficiency. The Blackwell iteration of NVIDIA Max-Q technology extends battery life by as much as 40%, including slim and lightweight laptops that preserve their elegant design without compromising power or performance.
NVIDIA DLSS 4 Enhances Performance by Up to 8x
DLSS 4 introduces Multi Frame Generation to enhance frame rates by employing AI to create up to three frames for every rendered frame. This functions collaboratively with the suite of DLSS technologies to elevate performance by as much as 8x compared to conventional rendering, while ensuring responsiveness through NVIDIA Reflex technology.
DLSS 4 also features the graphics industry’s inaugural real-time application of the transformer model architecture. Transformer-based DLSS Ray Reconstruction and Super Resolution models utilize 2x more parameters and 4x additional compute to provide enhanced stability, minimized ghosting, superior detail, and improved anti-aliasing in gaming environments. DLSS 4 will be available on GeForce RTX 50 Series GPUs in over 75 games and applications on launch day.
NVIDIA Reflex 2 presents Frame Warp, a groundbreaking method to diminish latency in games by updating a rendered frame based on the most recent mouse input just before it reaches the display. Reflex 2 can decrease latency by up to 75%. This improvement offers gamers a competitive advantage in multiplayer environments while making single-player titles more responsive.
Blackwell Introduces AI to Shaders
Twenty-five years ago, NVIDIA launched GeForce 3 and programmable shaders, which laid the foundation for two decades of graphic advancements, ranging from pixel shading to compute shading to real-time ray tracing. Alongside GeForce RTX 50 Series GPUs, NVIDIA is unveiling RTX Neural Shaders, which incorporate small AI networks into programmable shaders, unlocking cinematic-quality materials, lighting, and more in real-time gaming.
Rendering game characters is among the most difficult challenges in real-time graphics, as individuals tend to detect the tiniest errors or artifacts in digital representations. RTX Neural Faces takes a basic rasterized face and 3D pose data as input, utilizing generative AI to render a temporally stable, high-fidelity digital face in real time.
RTX Neural Faces is enhanced by new RTX technologies for ray-traced hair and skin. Coupled with the new RTX Mega Geometry, which allows up to 100x more ray-traced triangles in a scene, these innovations promise a significant advancement in realism for game characters and environments.
The potential of neural rendering, DLSS 4, and the novel DLSS transformer model is demonstrated on GeForce RTX 50 Series GPUs featuring Zorah, an innovative technology demonstration from NVIDIA.
Autonomous Game Characters
GeForce RTX 50 Series GPUs deliver industry-leading AI TOPS to empower autonomous game characters alongside game rendering.
NVIDIA is unveiling a suite of new NVIDIA ACE technologies that enable game characters to perceive, strategize, and act like human players. Characters powered by ACE are being integrated into KRAFTON’s PUBG: BATTLEGROUNDS and InZOI, the publisher’s forthcoming life simulation game, as well as Wemade Next’s MIR5.
In PUBG, companions empowered by NVIDIA ACE plan and execute tactical moves, collaborating with human players to secure survival. InZOI showcases Smart Zoi characters that autonomously modify their behaviors according to life objectives and in-game occurrences. In MIR5, large language model (LLM)-guided raid bosses alter strategies based on player actions, resulting in more dynamic and challenging encounters.
AI Foundation Models for RTX AI PCs
Demonstrating how RTX enthusiasts and developers can utilize NVIDIA NIM microservices to construct AI agents and assistants, NVIDIA is set to launch a series of NIM microservices and AI Blueprintsfor RTX AI PCs from leading model creators such as Black Forest Labs, Meta, Mistral, and Stability AI.
Applications encompass LLMs, visual language models, image creation, speech processing, embedding models for retrieval-augmented generation, PDF extraction, and computer vision. The NIM microservices incorporate all essential components required for executing AI on PCs and have been fine-tuned for implementation across all NVIDIA GPUs.
To illustrate how enthusiasts and developers can leverage NIM to create AI agents and assistants, NVIDIA today showcased Project R2X, a vision-capable PC avatar capable of providing information at a user’s fingertips, facilitating desktop applications and video conferencing, as well as reading and summarizing documents, among other tasks.
AI-Enhanced Tools for Creators
The GeForce RTX 50 Series GPUs amplify creative processes. RTX 50 Series GPUs are the pioneering consumer GPUs to accommodate FP4 precision, enhancing AI image generation efficiency for models like FLUX by 2x and allowing generative AI models to operate locally within a reduced memory footprint, as compared to prior-generation hardware.
The NVIDIA Broadcast application adds two AI-driven beta features for livestreamers: Studio Voice, which enhances microphone audio, and Virtual Key Light, which reilluminates faces for refined streaming. Streamlabs is launching the Intelligent Streaming Assistant, powered by NVIDIA ACE and Inworld AI, functioning as a co-host, producer, and technical aid to elevate livestreams.
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 debut on Jan. 30 at prices of $1,999 and $999, respectively.
The GeForce RTX 5070 Ti GPU with 1,406 AI TOPS and the GeForce RTX 5070 GPU with 988 AI TOPS will be launched starting in February at $749 and $549, respectively.
The NVIDIA Founders Editions of the GeForce RTX 5090, RTX 5080, and RTX 5070 GPUs will be procurable directly from nvidia.com and various retailers globally.
Standard-clocked and factory-overclocked versions will be offered by leading add-in card manufacturers such as ASUS, Colorful, Gainward, GALAX, GIGABYTE, INNO3D, KFA2, MSI, Palit, PNY, and ZOTAC, as well as in desktops from system builders including Falcon Northwest, Infiniarc, MAINGEAR, Mifcom, ORIGIN PC, PC Specialist, and Scan Computers.
Laptops equipped with GeForce RTX 5090, RTX 5080, and RTX 5070 Ti GPUs will become available starting in March, while RTX 5070 Laptop GPUs will be released in April by the world’s leading manufacturers, including Acer, ASUS, Dell, GIGABYTE, HP, Lenovo, MECHREVO, MSI, and Razer.
About NVIDIA
NVIDIA (NASDAQ: NVDA) stands as the global authority in accelerated computing.
For additional inquiries, please reach out to:
Ben Berraondo
NVIDIA Corporation
+1-669-271-5730
bberraondo@nvidia.com
Certain remarks in this announcement, including but not limited to, comments about: the advantages, impact, efficacy, and accessibility of NVIDIA’s products, services, and technologies, such as the GeForce RTX 50 Series Desktop and Laptop GPUs, NVIDIA Blackwell architecture, fifth-generation Tensor Cores, fourth-generation RT Cores, GeForce RTX 5090 Founders Edition GPU, NVIDIA DLSS 4, NVIDIA Reflex, DLSS Multi Frame Generation, DLSS Super Resolution and Ray Reconstruction models, NVIDIA Reflex 2, RTX Neural Shaders, RTX Neural Faces, RTX Mega Geometry, ACE technologies, NVIDIA NIM microservices, Project R2X, RTX 40 Series GPUs, NVIDIA RTX Remix modding platform, and D5 Render, NVIDIA Broadcast, Studio Voice, Virtual Key Light, GeForce Blackwell, NVIDIA Max-Q technology, GeForce RTX 5090, GeForce RTX 5080, GeForce RTX 5070 Ti, and GeForce RTX 5070, GeForce RTX 5090 Laptop GPU, GeForce RTX 5080 Laptop GPU, GeForce RTX 5070 Ti Laptop GPU, GeForce RTX 5070 Laptop GPU; along with third parties adopting NVIDIA’s products and technologies, are forward-looking statements that are subject to risks and uncertainties which could lead to significant differences in actual results as compared to expectations. Key factors that could result in actual variations include: global economic conditions; our dependency on third parties for manufacturing, assembling, packaging, and testing our products; effects of technological advancements and competition; development of new products and technologies or enhancements to existing products and technologies; market acceptance of our products or those of our partners; design, manufacturing or software flaws; shifts in consumer preferences or demands; alterations in industry standards and interfaces; unexpected loss of performance of our products or technologies when integrated into systems; as well as other factors discussed intermittently in the most recent reports NVIDIA submits to the Securities and Exchange Commission, or SEC, including, but not limited to, its annual report on Form 10-K and quarterly reports on Form 10-Q. Copies of reports filed with the SEC are posted on the company’s website and are accessible from NVIDIA without charge. These forward-looking statements do not guarantee future performance and reflect conditions only as of the date they are made, and, except as mandated by law, NVIDIA disclaims any obligation to update these forward-looking statements in light of future events or circumstances.
Numerous products and features referenced herein are in various stages of development and will be offered based on availability. The statements above do not represent, and should not be interpreted as, a commitment, pledge, or legal obligation, and the development, release, and timing of any features or functionalities described for our products are subject to alteration and remain at NVIDIA’s exclusive discretion. NVIDIA will bear no responsibility for any failure to deliver or delays in the provision of any of the products, features, or functions detailed herein.
© 2025 NVIDIA Corporation. All rights reserved. NVIDIA, the NVIDIA logo GeForce, and NVIDIA NIM are trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and other countries. Other company and product designations may be trademarks of relevant companies associated with them. Features, pricing, availability, and specifications are subject to modification without notice.
An image accompanying this announcement is accessible at