Nvidia is officially announcing its RTX 50 series GPUs today. After months of leaks and rumors, the next-generation RTX Blackwell GPUs are now official and there are four of them on the way.

Nvidia CEO Jensen Huang introduced the RTX 50 series GPUs during a CES keynote this evening, announcing an RTX 5090 for $1,999, an RTX 5080 for $999, an RTX 5070 Ti for $749 -Dollars and an RTX 5070 for $549. Nvidia’s new GPUs RTX 5090 and RTX 5080 will both be available on January 30th, with the RTX 5070 Ti and RTX 5070 following in February.

The RTX 50 Series GPUs feature a new Founders Edition design with just two dual flow fans, a 3D vapor chamber, and GDDR7 memory. All RTX 50 series cards are PCIe Gen 5 and feature DisplayPort 2.1b connectors to drive displays up to 8K and 165 Hz.

Surprisingly, the RTX 5090 Founders Edition will be a dual-slot GPU and will fit in small form factor PCs – a big departure from the size of the RTX 4090. The RTX 5090 features 32GB of GDDR7, a memory bandwidth of 1,792GB/sec. and a massive 21,760 CUDA cores. This all adds up to a GPU that Nvidia says will be twice as fast as the RTX 4090 thanks to DLSS 4 and the Blackwell architecture.

Nvidia demonstrated Cyberpunk 2077 runs on an RTX 5090 with DLSS 4 at 238 fps compared to 106 fps on an RTX 4090 with DLSS 3.5. Both GPUs run the game with ray tracing fully enabled.

The RTX 5080 is twice as fast as the RTX 4080 and has 16GB of GDDR7 memory, a memory bandwidth of 960GB/sec. and 10,752 CUDA cores. With the RTX 5080, Nvidia promises major performance improvements compared to the previous model, the RTX 4080.

Nvidia is also launching an RTX 5070 Ti and an RTX 5070. The RTX 5070 Ti features 16GB of GDDR7 memory, 896GB/s memory bandwidth, and 8,960 CUDA cores. The RTX 5070 features 12GB of GDDR7, 672GB/s memory bandwidth, and 6,144 CUDA cores. According to Nvidia, the RTX 5070 Ti will be twice as fast as the RTX 4070 Ti and the RTX 5070 will be twice as fast as the RTX 4070.

Nvidia is also bringing its RTX 50 series to laptops, with the RTX 5090 laptop GPU available with 24GB of GDDR7 memory for the first time. The RTX 5080 laptop GPU ships with 16GB of GDDR7 memory, the RTX 5070 Ti with 12GB of GDDR7 memory, and the RTX 5070 with just 8GB of GDDR7 memory. RTX 50 series laptops will be available from various PC manufacturers starting in March.

Huang demonstrated Nvidia’s RTX Blackwell GPUs with a real-time rendering demo at the start of the company’s CES keynote today. The demo included new RTX Neural Materials, RTX Neural Faces, text-to-animation and even DLSS 4. “The new generation of DLSS can generate beyond frames and predict the future,” says Huang. “We used GeForce to enable AI, and now AI is revolutionizing GeForce.”

Nvidia’s new RTX Neural Shaders can be used to compress textures in games, while RTX Neural Faces aim to improve facial quality using generative AI. The next generation of DLSS includes multi-frame generation, which Nvidia says generates up to three additional frames per traditional frame and can multiply frame rates by up to eight times compared to traditional rendering.

DLSS 4 also includes real-time application of transformers to improve image quality, reduce ghosting and add more detail to motion. The DLSS 4 upgrade even works on existing RTX GPUs as the features have been updated to the new Transformer AI models. You can read more about DLSS 4 here.

Nvidia’s announcement of the RTX 50 series comes more than two years after the announcement of the RTX 4090 and RTX 4080, which are based on Nvidia’s Ada Lovelace architecture. Nvidia’s RTX 40 GPU series focused on improving ray tracing with Deep Learning Super Sampling (DLSS) version 3, and the RTX 4090 delivered some truly impressive performance improvements over the previous RTX 3090 GPU.