Jensen Huang has now proudly shown off the new Nvidia GeForce RTX 5080 gaming GPU at the CES tradeshow in Las Vegas, where we were in attendance. This new graphics card is thankfully significantly cheaper than the RTX 4080, and it has a similar core spec, with 16GB of VRAM. We're confident that there isn't going to be any "unlaunching" this time around. In this guide, we'll take you through the RTX 5080 release date, as well as the price and specs of this new graphics card.
While the RTX 5080 review we found it to be an easy recommendation, despite a modest performance uplift over the RTX 4080 Super.
Nvidia GeForce RTX 5080 release date
The RTX 5080 release date was Thursday, January 30, 2025, coming just a few weeks after Nvidia unveiled the new GPU at the CES tradeshow in Las Vegas on January 6.
Nvidia GeForce RTX 5080 price
The RTX 5080 price is $999 for the MSRP, which refers to the Nvidia Founders Edition at stock speed. This matches the price of the RTX 4080 Super when it came out, and is also a good $200 cheaper than the original RTX 4080's price of $1,199.
Nvidia GeForce RTX 5080 specs
The Nvidia GeForce RTX 5080 specifications show it has a similar amount of power to the RTX 4080, with 16GB of VRAM and a 256-bit memory interface, although it also has the benefit of using GDDR7 memory.
| Nvidia GeForce RTX 5080 | |
| CUDA cores | 10,752 |
| Base clock | 2.3GHz |
| Boost clock | 2.62GHz |
| RT cores | 4th-gen, 171 TFLOPS |
| Tensor cores | 5th-gen, 1,801 AI TOPS |
| Interface | 16x PCIe 5.0 |
| VRAM | 16GB 32Gbps GDDR7 |
| Memory interface | 256-bit |
| Memory bandwidth | 960GB/s |
| Power draw | 360W |
| Power connector | 1 x 16-pin |
The Nvidia GeForce RTX 5080 is built on a new architecture, using one of the company's new Blackwell RTX 50 GPU designs. While the RTX 5090 is rumored to use a large new chip, codenamed GB202, the latest RTX 5080 leaks say that this new graphics card will use a smaller chip, codenamed GB203.
It's likely that this chip will also be used in other GPUs further down the Nvidia stack, such as the RTX 5070 Ti, with some parts of the GPU disabled, but the RTX 5080 is rumored to use a variant codenamed GB203-400-A1.
The RTX 5080 has 10,752 CUDA cores, which is less than half the number of the RTX 5090 although, to be fair, it is half the price. That's a similar number to the 10,240 CUDA cores found in the current RTX 4080 Super, but they're dramatically lower than the figures for the RTX 5090.
Similarly, the RTX 5080 has 16GB of GDDR7 memory at launch, and while this will be faster than the GDDR6X VRAM used in the RTX 4080, the amount stays the same. However, a recent leak claims that a 24GB RTX 5080 could be launched later, giving the card a bit more headroom for running games at high resolutions with lots of detail.
What's more, it's rumored that this 24GB card would have the same core GPU spec as the 16GB card, a feat that's now technically possible thanks to the new Samsung 24Gb GDDR7 chip that's just been announced. This chip has a 3GB capacity in the same package size as a 2GB chip, meaning it could be a drop-in replacement for 16GB cards.
Sadly, though, the memory interface has the same 256-bit width as the RTX 4080, which is disappointing at this price. Given that the RTX 5090 has a 512-bit interface, the RTX 5080 should arguably at least have a 320-bit bus and more VRAM.
On the plus side, the use of GDDR7 VRAM provides the RTX 5080 with plenty of bandwidth and this factor doesn't seem to overly affect the card's performance.
Finally, the RTX 5080 power draw is 360W, and it requires a 16-pin power connector and at least an 850W PSU.
Nvidia GeForce RTX 5080 benchmarks
Our Nvidia GeForce RTX 5080 benchmarks put the card as slightly faster than the RTX 4080 Super in rasterization and a bit quicker still ray tracing, but the card relies heavily on DLSS 4 Multi Frame Gen to really pull ahead of older cards.
In our RTX 5080 review we found that the RTX 5080 delivered as little as a 4.5% higher frame rate than the RTX 4080 Super in non-ray traced games such as Call of Duty: Black Ops 6. In Doom Eternal it was also just 5.2% faster.
Turning on ray tracing boosted performance more in some titles, with a 21% advantage in Indiana Jones and the Great Circle. However, turning on ray tracing in Doom Eternal only resulted in a 6.2% advantage.
Instead, it's down to DLSS 4 frame generation to really see this card pull ahead. Its ability to generate two or even three new frames with AI can quadruple perceived frame rates, in theory. In practice, we regularly saw frame rates double over what could be achieved with the single frame generation of DLSS 3 on RTX 4000 series cards. Only a few games have this feature, and only some will work well with it, but it's a powerful new tool in Nvidia's belt.
You can read our full guide to Nvidia DLSS, where we explore what makes Nvidia's upscaling and frame-generation tech tick.