New GeForce RTX 50 Series Graphics Cards & Laptops Powered By NVIDIA Blackwell Bring Game-Changing AI and Neural Rendering Capabilities To Gamers and Creators

Powered by the NVIDIA Blackwell RTX architecture, GeForce RTX 50 Series graphics cards and GeForce RTX 50 Series laptops accelerate frame rates by up to 8X using NVIDIA DLSS 4 with Multi Frame Generation, reduce latency by up to 75% using NVIDIA Reflex 2, enable next-level graphical fidelity for gamers and creators with NVIDIA RTX Neural Shaders, and much more.

GeForce RTX 50 Series GPUs and laptops deliver game-changing performance, power transformative AI experiences, and enable creators to complete workflows in record time. Rewatch the NVIDIA Keynote by NVIDIA CEO, Jensen Huang, below, and read on for all of the details.

Neural rendering is the next era of computer graphics. By integrating neural networks into the rendering process, we can take dramatic leaps forward in performance, image quality, and interactivity to deliver new levels of immersion.

The very first example of neural rendering was DLSS. We used lower resolution rendered frames as an input to a neural network, which was trained to output a full resolution frame. DLSS has since evolved to the point where it can generate entire frames and understand the composition of a scene including shadows, reflections, and occlusion to generate images that are better than native rendering. With the invention of DLSS 4 with Multi Frame Generation, working in unison with the complete suite of DLSS technologies, we can multiply frame rates by up to 8X over traditional brute-force rendering and provide image quality that is better than native rendering.

But DLSS is just the beginning.

We've integrated neural networks inside of programmable shaders to create neural shaders. RTX Neural Shaders will drive the next decade of graphics innovations. They can be used to compress textures by up to 7X, saving massive amounts of graphics memory. And be used to create cinematic-quality textures, and even more advanced lighting effects in games.

RTX Neural Faces offers an innovative, new approach to improve face quality using generative AI. Instead of traditional rendering, Neural Faces takes a simple rasterized face plus 3D pose data as input and uses a real-time generative AI model to infer a more natural face.

The NVIDIA RTX Blackwell architecture has been built and optimized for neural rendering. It has a massive amount of processing power, with new engines and features specifically designed to accelerate the next generation of neural rendering.

With up to 92 billion transistors, Blackwell is the most powerful consumer GPU ever created. The Blackwell streaming multiprocessor (SM) has been updated with more processing throughput, and a tighter integration with the Tensor Cores in order to optimize the performance of neural shaders. Blackwell is enhanced by several hardware and software innovations to improve Shader Execution Reordering. The reorder logic is twice as efficient, increasing the speed and precision of reordering which accelerates the performance of neural shaders.

New Blackwell Tensor Cores have been built with a massive amount of AI processing horsepower, and support accelerated processing of FP4 precision models. With FP4, Blackwell Tensor Cores can not only process models faster, but can do so while using less graphics memory.

To help support the frame pacing requirements of next generation DLSS Multi Frame Generation, the Blackwell architecture was built with enhanced hardware flip metering capabilities to provide the speed and accuracy required for a smooth, high-quality experience.

Blackwell also features brand new RT Cores designed to ray trace massive amounts of detailed geometry. The RT Cores have 2X the ray triangle intersection rate of the previous generation, and enhanced compression designed to reduce memory footprint. This allows Blackwell GPUs to ray trace levels of geometry that were never before possible.

Blackwell has also been enhanced with PCIe Gen5 and DisplayPort 2.1b UHBR20, driving displays up to 8K 165Hz.

For GeForce RTX 50 Series laptops, new Max-Q technologies such as Advanced Power Gating, Low Latency Sleep, and Accelerated Frequency Switching increases battery life by up to 40%, compared to the previous generation.

And in order to feed all this processing power, Blackwell is equipped with the world's fastest memory - GDDR7 with speeds up to 30Gbps. With G7 memory, Blackwell GPUs can deliver up to 1.8TB/s of memory bandwidth.

On January 30th, the GeForce RTX 5090 and GeForce RTX 5080 arrive on store shelves. The GeForce RTX 5070 Ti and GeForce RTX 5070 will be available starting in February.

Limited NVIDIA Founders Edition models of the GeForce RTX 5090, GeForce RTX 5080, and GeForce RTX 5070 graphics cards will be available worldwide. And stock-clocked and factory-overclocked variants of all four GPUs will be available from top add-in card providers such as ASUS, Colorful, Gainward, GALAX, GIGABYTE, INNO3D, KFA2, MSI, Palit, PNY and ZOTAC. And in desktops from system builders, including Falcon Northwest, Maingear, Origin PC, and more.

Thanks to the Blackwell architecture’s innovations and DLSS 4, the GeForce RTX 5090 outperforms the GeForce RTX 4090 by 2X.

Cyberpunk 2077: Phantom Liberty on GeForce RTX 5090 runs two times faster than last generation with the power of DLSS 4

With 32GB of GDDR7 memory, 1792 GB/sec of total memory bandwidth, 21,760 CUDA Cores, 680 5th Generation Tensor, and 170 4th Generation Ray Tracing Cores, it is the ultimate GeForce GPU, with more hardware and power than anything we’ve made previously (see the complete list of specs here). 

In games, DLSS 4 with Multi Frame Generation helps multiply performance in Cyberpunk 2077, Alan Wake 2, and Black Myth: Wukong, enabling GeForce RTX 5090 owners to play at 4K 240Hz/FPS with full ray tracing and every other setting maxed out, for the definitive experience.

In Generative AI applications, image generation is 2X faster with half the memory using FP4 on the GeForce RTX 5090, compared to FP16 on the GeForce RTX 4090. FP4 is a lower quantization method, similar to file compression, decreasing model sizes. 

Black Forest Labs’ FLUX.1 [dev] model requires over 23GB of VRAM in plain FP16. On the GeForce RTX 4090, images are generated in 15 seconds. With FP4, less VRAM is used and the GeForce RTX 5090 can reduce image generation to just over five seconds.

The GeForce RTX 5090 will be available from January 30th, starting at €2329.

Our limited NVIDIA GeForce RTX Founders Edition graphics cards are the pinnacle of design, built with premium materials, boasting striking, unique designs, and cooling innovations.

For the GeForce RTX 5090, our engineers have created an unbelievable 2-slot, 304mm long x 137mm high x 2-slot wide, SFF-Ready Enthusiast GeForce Card capable of quietly cooling the high-performance Blackwell GPU inside thanks to a revolutionary new double flow through design.

Each aspect of the new GeForce RTX 5090 Founders Edition has been purposefully designed to increase cooling capacity and capabilities by leveraging new design innovations, Liquid Metal thermal interface material (TIM), and a unique 3-piece PCB. Stay tuned for further details about the design of these incredible cards ahead of their release.

The GeForce RTX 5080 is up to twice the speed of the GeForce RTX 4080 in games, thanks to the Blackwell architecture and DLSS 4 with Multi Frame Generation. With new 5th gen Tensor Cores, 4th gen RT Cores, and 16GB of GDDR7 memory providing up to 960 GB/sec of total memory bandwidth (a 34% increase compared to the GeForce RTX 4080’s 717 GB/sec), the GeForce RTX 5080 delivers a massive leap in performance for gamers and creators.

At 4K, with full ray tracing and other settings maxed, GeForce RTX 5080 owners can play Alan Wake 2, Black Myth: Wukong, and Cyberpunk 2077 at high frame rates, with performance that’s around twice as fast, on average, compared to the GeForce RTX 4080.

The GeForce RTX 5080 will be available from January 30th, starting at €1169.

The GeForce RTX 5070 Ti includes 16GB of GDDR7 memory, and 896 GB/sec of total memory bandwidth, a 78% increase in bandwidth compared to the GeForce RTX 4070 Ti’s 504 GB/sec.

Using the full capabilities of the Blackwell architecture, and the power of DLSS 4 with Multi Frame Generation, game frame rates are 2X faster than the GeForce RTX 4070 Ti’s. At 2560x1440, with full ray tracing and other settings maxed, GeForce RTX 5070 Ti owners can play Alan Wake 2, Black Myth: Wukong, and Cyberpunk 2077 at high frame rates.

The GeForce RTX 5070 Ti will be available starting at €879.

The GeForce RTX 5070 sports the powerful new cores of the NVIDIA Blackwell architecture 12GB GDDR7 memory, and has 672 GB/sec of total memory bandwidth, compared to the GeForce RTX 4070’s 504 GB/sec.

At 2560x1440, with full ray tracing and other settings maxed, and DLSS Multi Frame Generation enabled, GeForce RTX 5070 owners can play Black Myth: Wukong, Alan Wake 2, and Cyberpunk 2077 at high frame rates, with performance that is twice as fast on average compared to the GeForce RTX 4070.

The GeForce RTX 5070 will be available starting at €649.

Starting in March, the GeForce RTX 50 Series comes to laptops. As thin as 14.9mm, GeForce RTX 50 Series laptops boast up to 40% better battery life thanks to new Blackwell Max-Q innovations, and double the performance of previous-generation models.

Game with double the FPS. Create content and complete workflows in half the time. And finish generative AI tasks 2.5X faster.

Blackwell Max-Q is designed from the ground up for efficiency, delivering a massive leap in performance and battery life. There are a number of Max-Q innovations in the Blackwell architecture that combine to make this possible.

Advanced Power Gating technologies greatly reduce power by rapidly toggling unused parts of the GPU.

Blackwell has significantly faster low power states. Low Latency Sleep allows the GPU to go to sleep more often, saving power even when the GPU is being used. This reduces power for gaming, Small Language Models (SLMs), and other creator and AI workloads on battery.

Accelerated Frequency Switching boosts performance by adaptively optimizing clocks to each unique workload at microsecond level speeds.

Voltage Optimized GDDR7 tunes graphics memory for optimal power efficiency with ultra low voltage states, delivering a massive jump in performance compared to last-generation’s GDDR6 VRAM.

Altogether, battery life is boosted by up to 40% compared to previous generation GeForce RTX Laptops.

The GeForce RTX 5090 Laptop GPU is the ultimate GeForce Laptop GPU for gaming and creating. 10,496 CUDA Cores, 1,824 AI TOPS, and 24GB of GDDR7 memory give it unmatched capabilities and performance. Creative and generative AI workloads benefit from the largest ever frame buffer in a laptop, and with the first ever deployment of three NVIDIA NVENC encoders in a laptop, video workflows can be completed in record time.

The GeForce RTX 5080 Laptop GPU boasts 7,680 CUDA cores, 1,334 AI TOPS, and 16GB of GDDR7 memory, with 2X the performance of the GeForce RTX 4080 Laptop GPU. For creators, the 2X increase in memory bandwidth will benefit 3D rendering and video editing.

GeForce RTX 5070 Family Laptop GPUs include two different GPUs. The GeForce RTX 5070 Ti Laptop GPU boasts 5,888 CUDA cores, 992 AI TOPS, and 12GB of GDDR7 memory. And the GeForce RTX 5070 Laptop GPU boasts 4,608 CUDA cores, 798 AI TOPS, and 8GB of GDDR7 memory. 

GeForce RTX 5090, GeForce RTX 5080, and GeForce RTX 5070 Ti laptops will be available starting in March, followed by GeForce RTX 5070 Laptops in April. There will be designs from the world’s top manufacturers, including Acer, ASUS, Dell, GIGABYTE, HP, Lenovo, MECHREVO, MSI, and Razer. Stay tuned to their websites for further details about the GeForce RTX 50 Series Laptops they’re creating.

Leveraging the new capabilities of the Blackwell architecture, GeForce RTX 50 Series users will enjoy record-breaking performance, even more responsive gameplay, movie-quality visuals, and new applications of AI that further enhance games and apps.

NVIDIA DLSS is a suite of neural rendering technologies powered by GeForce RTX Tensor Cores that boosts frame rates while delivering crisp, high-quality images that rival native resolution rendering, as part of over 700 RTX games and apps.

At CES 2025, we’re advancing DLSS once again with the introduction of DLSS 4, featuring Multi Frame Generation for GeForce RTX 50 Series GPUs. DLSS Multi Frame Generation generates up to three additional frames per traditionally rendered frame, working in unison with the complete suite of DLSS technologies to multiply frame rates by up to 8X over traditional brute-force rendering. This massive performance improvement on GeForce RTX 5090 graphics cards unlocks stunning 4K 240 FPS fully ray-traced gaming.

On the GeForce RTX 5090, DLSS 4 with Multi Frame Generation multiplies performance by over 8X versus traditional brute force rendering in this Cyberpunk 2077 scene, PC latency is halved for more responsive gameplay, and image quality is further enhanced

DLSS 4 also introduces the biggest upgrade to its AI models since the release of DLSS 2.0 in 2020.

DLSS Ray Reconstruction, DLSS Super Resolution, and DLAA will now be powered by the graphics industry’s first real-time application of ‘transformers’, the same advanced architecture powering frontier AI models like ChatGPT, Flux, and Gemini. DLSS transformer models improve image quality with improved temporal stability, less ghosting, and higher detail in motion.

Watch NVIDIA’s Bryan Catanzaro and Edward Liu walk through DLSS 4

Get all the details here, in our DLSS 4 announcement article.

In competitive games, a few milliseconds of input lag can mean the difference between victory and defeat.

In 2020, we released NVIDIA Reflex, an innovative technology that reduces PC latency in top competitive games by an average of 50%. NVIDIA Reflex accomplishes this by synchronizing CPU and GPU work, so player actions are reflected in-game quicker, giving gamers a competitive edge in multiplayer games, and making single-player titles more responsive.

At CES 2025, we’re unveiling NVIDIA Reflex 2, which can reduce PC latency by up to 75%. Reflex 2 combines Reflex Low Latency mode with a new Frame Warp technology, further reducing latency by updating the rendered game frame based on the latest mouse input right before it is sent to the display.

Learn more in our NVIDIA Reflex 2 announcement article.

The GeForce RTX 50 Series revolutionizes creative workflows thanks to new NVIDIA Studio tools and features for creators, and even faster hardware.

Added hardware support for encoding and decoding the 4:2:2 pro-grade color format yields a staggering 11X encoding speed increase compared to software encoders.

9th Gen NVENC video encoders include a 5% improvement to HEVC and AV1 encoding quality, and a new AV1 Ultra Quality mode that offers an additional 5% improvement to encoding efficiency. And the 6th Gen NVIDIA decoder is capable of decoding and playing back up to eight 4K60 4:2:2 video streams simultaneously.

Livestreamers get 2 new AI upgrades: an AI Agent from Streamlabs - the Intelligent Streaming Assistant powered by NVIDIA ACE and Inworld AI - capable of joining you on stream as a sidekick, helping you produce your streams, or assisting you with any technical issues. And a new NVIDIA Broadcast upgrade, which offers 2 new effects - Studio voice to improve your microphone quality, and Virtual Key Light to relight you with AI.

DLSS Multi Frame Generation further boosts viewport framerates in creative apps - paired with new-generation RT Cores, GeForce RTX 50 Series GPUs deliver 2X the performance over the previous generation when editing 3D scenes in applications like D5 Render.

NVIDIA RTX Remix is adding RTX Neural Rendering technologies and even more features in the near future.

RTX Video, which upscales video by removing compression artifacts and sharpening edges, and RTX Video HDR, which converts standard dynamic range video into vibrant high dynamic range, is getting an update to decrease GPU usage by 30%. And RTX Video Super Resolution can now upscale HDR10 video content as well.

Get further details in the new GeForce RTX 50 Series NVIDIA Studio blog.

NVIDIA ACE is a suite of digital human technologies that bring game characters and digital assistants to life with generative AI. Powered by GeForce RTX AI PCs and laptops, ACE characters use AI to perceive, plan and act like human players. Play cooperatively with AI companions, battle enemies that continuously learn from player behavior, and interact with autonomous NPCs driven by their own motivations and objectives in persistent living worlds.

Head to our NVIDIA ACE games article to see how NVIDIA ACE technologies are being used to create autonomous AI companions, bosses, and more in inZOI, MIR5, NARAKA: BLADEPOINT MOBILE PC VERSION, PUBG: BATTLEGROUNDS, and more.

Project G-Assist will add an experimental AI assistant to your GeForce RTX AI PC. Accessible via the NVIDIA app overlay, the experimental release of Project G-Assist enables you to command your system and optimize its performance and efficiency with simple commands. Chart frame rates, latency, power consumption, and other performance statistics, and control connected peripherals and accessories, including peripheral lighting, fan speeds, and even home LED lighting.

To demonstrate how RTX enthusiasts and developers can use NIM microservices to build AI agents and assistants, we previewed Project R2X, a vision-enabled PC avatar that can put information at a users’ fingertips, assist with desktop apps and video conference calls, read and summarize documents, and more.

R2X can be connected to cloud AI services such as OpenAI’s GPT4o and xAI’s Grok, and NIM microservices and AI Blueprints, such as PDF retrievers or alternative LLMs, via developer frameworks such as CrewAI, Flowise AI, and Langflow. Sign up to follow along with Project R2X updates.

With double the performance of previous-generation GPUs, 40% longer laptop battery life, and a suite of neural rendering capabilities, GeForce RTX 50 Series products are game changing. Your performance in today’s games and apps multiplies massively with DLSS Multi Frame Generation, FP4, and other enhancements. And in the rapidly approaching future, you can take full advantage of RTX Neural Rendering to game and create with film-quality visuals.

Stay tuned to GeForce.com for further information about the GeForce RTX 50 Series as we approach the release of our new generation of GPUs and laptops, and for all our future game and technology announcements.

In the meantime, check out all of our other GeForce RTX 50 Series announcements to see how we’re further improving your experiences in games and apps, and delivering new innovations that advance the PC industry.