Nvidia has good and bad news for people building or buying gaming PCs.
The good news is that three of their four new RTX 50 series GPUs are the same price or slightly cheaper than the RTX 40 series GPUs they are replacing. The RTX 5080 costs $999, the same price as the RTX 4080 Super; The 5070 Ti and 5070 launch for $749 and $549, each $50 less than the 4070 Ti Super and 4070 Super.
The bad news for people looking for the fastest card they can get is that the company is charging $1,999 for its flagship RTX 5090 GPU, significantly more than the RTX 4090's $1,599 MSRP. If you want Nvidia's biggest and best , it will cost you at least up to four high-end gaming consoles or a couple of mid-range gaming PCs with decent specs.
Pricing for the first batch of Blackwell-based RTX 50 series GPUs. Credit: Nvidia
Nvidia also announced a new version of its upscaling algorithm, DLSS 4. As with DLSS 3 and the RTX 40 series, the flagship DLSS 4 feature will be exclusive to the 50 series. It's called DLSS Multi Frame Generation and, like its As the name suggests, it takes the Frame Generation feature of DLSS 3 and allows you to generate even more frames. That's why Nvidia CEO Jensen Huang claimed that the $549 RTX 5070 performed like the $1,599 RTX 4090; That's also why those claims are a bit misleading.
The launch will begin with RTX 5090 and 5080 on January 30. The 5070 Ti and 5070 will follow sometime in February. All cards except the 5070 Ti will come in Founders Editions designed by Nvidia, as well as designs made by Nvidia partners; the 5070 Ti will not receive a Founders Edition.
The RTX 5090 and 5080
| RTX 5090 | RTX 4090 | RTX 5080 | RTX 4080 Super | |
|---|---|---|---|---|
| CUDA cores | 21,760 | 16,384 | 10,752 | 10,240 |
| impulse clock | 2,410MHz | 2,520MHz | 2.617MHz | 2,550MHz |
| Memory bus width | 512 bit | 384 bit | 256 bit | 256 bit |
| Memory bandwidth | 1,792 GB/s | 1,008 GB/s | 960GB/s | 736GB/s |
| Memory size | 32GB GDDR7 | 24GB GDDR6X | 16GB GDDR7 | 16GB GDDR6X |
| TGP | 575 watts | 450W | 360W | 320 watts |
The RTX 5090, based on Nvidia's new Blackwell architecture, is a gigantic chip with 92 billion transistors. And while it costs twice as much as an RTX 5080, you also get twice as many GPU cores, twice as much RAM, and almost twice as much memory bandwidth. Even more so than the 4090, it's positioning itself head and shoulders above the rest of the GPUs in the family, and the 5080's performance won't come close to that.