The Nvidia GeForce RTX 50 Family announced

The rumors are now over at Nvidia side and we are in the new generation of GeForce RTX with GeForce RTX 50 family and debuting are the Nvidia GeForce RTX 5090, GeForce RTX 5080, GeForce RTX 5070 Ti and the GeForce RTX 5070 which were presented at Nvidia’s turn at the main stage of CES 2025.

Lets start with the GeForce RTX 5090 and this of course and for yet another generation without Blackwell architecture being a difference, the flagship.

The GeForce RTX 5090 includes 32GB of GDDR7, a memory bandwidth of 1,792GB/sec, and a massive 21,760 CUDA cores and the bad news is that the GPU card will consume up to 575 watts and Nvidia recommends using PSU with 1000 watts as minimum.

That’s 125 watts more than the RTX 4090, but Nvidia justifies it as precisely, the 5090 doubles its predecessor’s performance.

The GeForce RTX 5090 will have a Founder Edition or the reference that Nvidia sells directly to customer.

Next, the GeForce RTX 5080 which will be aimed directly to consumer 4K gaming resolution, include 16GB of GDDR7 memory, a memory bandwidth of 960GB/sec, and 10,752 CUDA cores. The RTX 5080 will have a total graphics power of 360 watts and Nvidia is recommending a 850-watt power supply.

As the situation for the 5090, Nvidia claims that it doubles the performance of GeForce RTX 4080 of 2022.

In my opinion, the surprise of the keynote was the announcement of both the GeForce RTX 5070 and the RTX 5070 Ti, normally a model serving as a refresher of the base model.

Nevertheless, the RTX 5070 has 12GB of GDDR7, a memory bandwidth of 672 GB/sec, and 6,144 CUDA cores and meanwhile, the GeForce RTX 5070 Ti includes 16GB of GDDR7 memory, a memory bandwidth of 896GB/s, and 8,960 CUDA cores.

Being already a repetitive claim, Nvidia says that both RTX 5070 and the Ti will be 2x faster than their respective predecessors and yes, lest talk about power consumption with the RTX 5070 Ti will have a total graphics power of 300 watts and require a 750-watt PSU, while the RTX 5070 has a total graphics power of 250 watts and only needs a 650-watt PSU.

All mentioned GPU cards will have a Founders Edition and expect Nvidia’s partner to have their own designs.

MSRP prices for the Founder editions goes as follow:

RTX GeForce 5090 – $1999
RTX GeForce 5080 – $999
RTX GeForce 5070 Ti – $759
RTX GeForce 5070 – $549

Nvidia confirmed a January 30th release for each individual Founders Edition, meanwhile partner’s variants availability were not immediately shared.

About the novelties of Blackwell architecture

The Blackwell architecture enabled Nvidia to have the hardware foundation for the next generation of it solution for AI based graphical upscaler, the DLSS 4, improving massively on ray tracing processing and Multi Frame Generation, which generates up to three additional frames per traditional frame and can multiply frame rates.

DLSS 4 also includes a real-time application of transformers to improve image quality, reduce ghosting, and add higher detail in motion a big differential with today’s AMD announcement on FSR 4, Nvidia opted to have DLSS 4 available for 2022’s Lovelace architecture.

Also, Nvidia demoed what they call RTX Neural Shaders, RTX Neural Faces, text to animation and starting with the first one, the job of the RTX Neural Shaders is to compress textures in games, while RTX Neural Faces aim to improve face quality using generative AI.

RTX 50 for gaming Laptops

Nvidia also confirmed that the mobile version of the RTX GeForce 50 family are coming this year for gaming laptop and includes the the RTX 5090 laptop GPU debuting with 24GB of GDDR7 memory. The RTX 5080 laptop GPU will ship with 16GB of GDDR7 memory, the RTX 5070 Ti with 12GB of GDDR7 memory, and the RTX 5070 with just 8GB of GDDR7 memory.

We should be hearing announcement soon and releases as early as March 2025.