Now the lid has been officially lifted Nvidia GeForce RTX 5090we had the opportunity to try out one of the new graphics cards at CES. Some rumors about the specs have turned out to be true, with Nvidia also offering DLSS 4 and new neural rendering technology for its new Blackwell lineup of gaming GPUs.

Nvidia CEO Jensen Huang revealed details of the new Nvidia Blackwell series at CES, which we attended, and when it launches it looks likely to be the best graphics card in terms of raw performance. In this guide, we’ll take you through the new GPU’s release date, specs, and price, and we’ll also show you what the Founders Edition card will look like with its new, cooler design.

Nvidia GeForce RTX 5090 release date

The RTX 5090 release date is Thursday, January 30, 2025. When Nvidia says the new GPU will be available. Nvidia announced the new GPU at CES 2025 on January 6.

Nvidia GeForce RTX 5090 price

RTX 5090 priced at $1,999 Going by the MSRP, we expect that to be what the Founders Edition will cost at launch. We expect third-party overclocked graphics cards to be more expensive. This price is significantly higher than the RTX 4090’s MSRP of $1,599, although it’s rare to find a 4090 at this price these days.

Nvidia GeForce RTX 5090 specifications

RTX 5090 specifications include 32GB GDDR7 VRAM and 21,760 CUDA cores, as well as a huge memory bandwidth of 1,792GB/s.

The RTX 5090 has 21,760 CUDA cores, which appear to be divided into 170 streaming multiprocessors (SM), which also means it has 170 RT cores. For comparison, the GeForce RTX 4090 has 128 SMs and has 16,384 CUDA cores, which means the RTX 5090 may have more parallel processing capabilities.

However, this isn’t an apples-to-apples comparison, as the RTX 5090 will be built using the Blackwell architecture rather than the Ada Lovelace architecture used by the 4090, and the performance of each core may vary.

We also had the chance to get our hands on the Founders Edition of the new graphics card to take a look at its design, and Nvidia has been very successful in plugging it into two slots. There are two fans on the front and just the vents on the back, and between them is the tiny RTX 5090 PCB, pictured above.

As widely speculated, the RTX 5090 also uses GDDR7 VRAM connected to an ultra-wide 512-bit bus, which is much wider than the RTX 4090’s already wide 384-bit interface. The result is a massive 1,792GB/s of memory bandwidth, showing that the VRAM’s effective speed is about 28Gbps. That’s huge compared to the RTX 4090’s bandwidth of just over 1TB/s.

Not only that, but the RTX 5090 is equipped with 32GB of large-capacity GDDR7 VRAM, providing plenty of space for professional work and gaming at very high resolutions with all settings maxed out.

All of these features come with a potential cost, though, and that’s the RTX 5090’s power consumption. Nvidia says the card’s total power consumption is a whopping 575W, but that still means the regular-speed card only requires a single 16-pin power cable, refuting previous speculation that the RTX 5090 would require two 16-pin power cables.

As expected, the GeForce RTX 5090 is also Nvidia’s first gaming GPU to use the new 16x PCIe 5.0 interface. You can still install it in a PCIe 4.0 or even a PCIe 3.0 slot, but you won’t get the full bandwidth, which may limit the performance of a PCIe 3.0 motherboard.

Finally, Nvidia has put the RTX 5090 frequency rumors to rest and confirmed that the RTX 5090 will have a boost clock frequency of 2.41GHz and a base clock frequency of 2.01GHz.

In the meantime, if you’re in the market for a new graphics card now, check out our GeForce RTX 4080 Super review, where we benchmark Nvidia’s latest high-end GPU. It corrects the huge pricing mistake Nvidia made with the original RTX 4080, while also delivering decent 4K gaming performance for $999.