Nvidia during their CES 25 show, unveiled their new 50 series GPUs using the Blackwell architecture.

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.

During the CES keynote, Jensen Huang mentioned Nueral Rendering saying..

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.

You can catch the keynote below.

What’s new with the Blackwell architecture?

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.

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). 

GeForce RTX 50 Series Graphics Cards

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.