Nvidia revealed its next generation of graphics cards, the GeForce RTX 50 series, at CES this week. There are four new GPUs in the lineup: the Geforce RTX 5090, 5080, 5070 and 5070 Ti.
The flagship card, the RTX 5090, costs $2,000, and Nvidia claims it’s twice as powerful as the RTX 4090, but requires a 1,000-watt power supply, which is a huge jump in power consumption base 450 W of the RTX 4090. Despite its power demand, the RTX 5090 is more compact than its predecessor and fits smaller PCs.
The slimmer size and higher performance hold true for all cards in the lineup, with Nvidia claiming the $1,000 RTX 5080 is twice as fast as the RTX 4080. The affordable $550 RTX 5070 offers performance comparable to that of the RTX 4090, at almost a third of the price. The 5070 Ti, meanwhile, falls between the 5070 and 5080 in terms of price ($750) and performance.
Rather than relying on pure processing power to achieve these benchmarks, the new 50 series cards leverage Nvidia’s latest machine learning technology, including RTX Neural Shaders and the latest DLSS 4 upscaling Not only does DLSS 4 allow upscaling of low-resolution gameplay to 1440p or 4K resolutions, but it also includes multi-frame generation, which Nvidia claims is capable of. generate up to three additional frames for each rendered gameplay frame. It’s basically doing for games what image smoothing does for movies and TV and creating the appearance of higher, smoother frame rates without the hardware actually rendering them.
So even though the actual hardware performance improvement of the 50 series GPUs is technically lower in terms of raw processing power without the help of AI technology (the 5070 has less processing power than the 4090, for example ), this also means that GPUs perform better. smaller and more affordable compared to their previous generation counterparts because you don’t need as much power to achieve high-end results.
Of course, AI scaling and frame generation have trade-offs compared to hardware rendering. These machine learning technologies can potentially match the hardware, making the quantity performance, but the problem is the quality of this performance. Upscalers like DLSS, AMD’s FSR, and Sony’s PSSR on PS5 Pro can be inconsistent (or even incorrect, in extreme cases), while frame generation can introduce noticeable input lag – somewhat something that playing at high frame rates is meant to alleviate, not exacerbate. .
To be fair, these are issues that Nvidia – and game developers – are aware of and are actively working to resolve. Additionally, many games already use these features to achieve great results, and the 40 series cards used DLSS to achieve large performance gains over the 30 series. Unfortunately, this was also incredibly expensive. If the next generation of technology works as expected, the 5090 could enable another massive performance boost, while mid-range RTX 50 GPUs could offer a much more affordable option for getting 4K resolution gameplay and high FPS.
Where to pre-order the GeForce RTX 5090, 5080, 5070 Ti and 5070
If you’re sold on Nvidia’s promise of AI-driven graphics processing, you’ll be happy to know that the new GPUs will be launching soon. The RTX 5090 and RTX 5080 launch on January 30, while the 5070 and 5070 Ti arrive in February. Although pre-orders aren’t live yet, listings for the GeForce RTX 5090 and RTX 5080 GPUs are live at Best Buy, and you can sign up to be notified as soon as they become available for purchase. We will update this article once pre-orders are available.
Note that these lists are for Nvidia’s reference card models; Third-party 50-series GPUs will likely roll out shortly after the Nvidia models launch. Nvidia also confirmed that RTX 50 series laptop GPUs are on the way, with the first models expected in March.
Nvidia GeForce RTX 50 Series GPU Pre-Orders
- GeForce RTX 5090 – $2,000 | Launching January 30
- GeForce RTX 5080 – $1,000 | Launching January 30
- GeForce RTX 5070 Ti – $750 | Launch in February
- GeForce RTX 5070 – $550 | Launch in February
