At CES 2025, Nvidia officially announced the new RTX 50XX series of graphics cards, which are made with Blackwell architecture. These new GPUs include both fifth-generation Tensor Cores and fourth-generation RT Cores, which allows for breakthroughs in AI-driven rendering, including neural shaders, digital human technologies, geometry and lighting.

The GeForce RTX 5090 GPU — the fastest GeForce RTX GPU to date — features 92 billion transistors, providing over 3,352 trillion AI operations per second (TOPS) of computing power. Blackwell architecture innovations and DLSS 4 mean the GeForce RTX 5090 GPU outperforms the GeForce RTX 4090 GPU by up to 2x.

GeForce Blackwell comes to laptops with all the features of desktop models, bringing a considerable upgrade to portable computing, including extraordinary graphics capabilities and remarkable efficiency. The Blackwell generation of NVIDIA Max-Q technology extends battery life by up to 40%, and includes thin and light laptops that maintain their sleek design without sacrificing power or performance.

One of the significant additions with the new series cards is DLSS 4. DLSS 4 introduces Multi Frame Generation to boost rates by using AI to generate up to three frames per rendered frame. It works in conjunction with the suite of DLSS technologies to increase performance by up to 8 over traditional rendering while maintaining responsiveness with NVIDIA Reflex technology.

DLSS4 also introduces the graphics industry’s first real-time of the transformer model architecture. Transformer-based DLSS Ray Reconstruction and Super Resolution models use twice as many parameters and four times more compute to provide stability, reduced ghosting, higher details, enhanced anti-aliasing game scenes. DLSS 4 will be supported on Ge RTX 50 Series GPUs in over 75 games and applications at launch.

NVIDIA Reflex 2 introduces Frame Warp, an innovative technique to reduce latency in games by updating a rendered frame based on the latest mouse input just before it is sent to the display. Reflex 2 can reduce latency by up to 75%, giving gamers a competitive edge in multiplayer games and making single-player titles more.

Of course, new cards means new specs and with four models launching in the next few weeks, there is a lot to learn. The below comparison graph shows off how each different card stacks up, with the RTX 5090 being the biggest powerhouse of the lot.

So that is a lot of power, but what does it cost? Well the prices range from ok to insane. The below are the starting prices for each of the models:

GeForce RTX 5090 - $4039

GeForce RTX 5080 - $2019

GeForce RTX 5070 Ti - $1509

GeForce RTX 5070 - $1109

You can sign up to be notified when the cards are available for order direct from Nvidia. Click here for the 5090, click here for the 5080 and click here for the 5070 family. There is no local date for any of the cards yet, we are usually a week or two after North America.

The full breakdown of information can be found here, and there is a lot of it. But as always, the real test will come once people start going hands on with the cards.