Skip to main content

Nvidia may give the RTX 5080 a sweet consolation prize

The back of the Nvidia RTX 4080 Super graphics card.
Jacob Roach / Digital Trends

Nvidia’s best graphics cards are due for an update, and it seems that the RTX 5080 might get an unexpected boost with faster GDDR7 memory than even the flagship RTX 5090. That might be its sole consolation prize, though, because the gap between the two may turn out to be even bigger than in this generation.

First, the good news. Wccftech cites its own sources as it reports that the RTX 5080 will get 32Gbps memory modules from the get-go — a significant upgrade over the RTX 5090 with its 28Gbps. The best part is that such a memory upgrade would bring the RTX 5080 to a whopping 1TB/s of total bandwidth, marking a huge improvement over the RTX 4080 Super, which maxes out at 736GB/s.

Recommended Videos

As we’ve noted in our RTX 50-series roundup, the RTX 5080 is said to sport 16GB of VRAM across a 256-bit memory bus. Recent leaks revealed that a 24GB version may also be unveiled one day, but that’s mere speculation at this point. Still, with 3GB GDDR7 modules said to come out a bit later, Nvidia will have room for solid upgrades down the line.

The bad news? I can’t help but feel like Nvidia might be doubling down on a decision it made in this generation. The RTX 4090 and the RTX 4080 had a massive performance and spec gap. At the time of launch, this actually made the $1,600 (and up) RTX 4090 a better deal than the $1,200 RTX 4080. The Super version at $1,000 made the performance-per-dollar aspect better, but the specifications stayed nearly the same.

The Nvidia RTX 4080 Super on a pink background.
Jacob Roach / Digital Trends

All leaks so far point to the RTX 5080 being a much weaker offering than the RTX 5090. The flagship is said to come with 21,760 CUDA cores and up to 32GB of GDDR7 memory across a 512-bit memory bus. Meanwhile, the RTX 5080 will reportedly max out at 10,752 CUDA cores, which is a measly upgrade over the RTX 4080 Super — and miles behind the RTX 5090. In addition to the above, Wccftech and other sources also report that the RTX 5080 might receive a significantly higher total board power (TBP) reaching 400 watts. Meanwhile, the RTX 5090 will max out the 12VHPWR connector at 600 watts.

All of this is speculation, but if the two cards indeed launch with these exact specs, the RTX 5080 may be up to 50% worse than the RTX 5090 — but we’ll have to wait and see. According to various leaks, the RTX 5090 and the RTX 5080 will hit the market first, with an announcement reportedly planned for CES 2025 in January.

Monica J. White
Monica is a computing writer at Digital Trends, focusing on PC hardware. Since joining the team in 2021, Monica has written…
Nvidia’s RTX 5080 laptop GPU almost makes the flagship obsolete
Upcoming Nvidia RTX 40-series laptops over a black and green background.

Nvidia makes some of the best graphics cards to be found in laptops, but some of these GPUs might be closer in terms of performance than you'd expect. The laptop version of the RTX 5080 has been benchmarked, and it's shockingly close to the RTX 5090. Are the laptops equipped with the RTX 5090 still worth buying?

Notebookcheck was able to compare the RTX 5090 and the RTX 5080 laptop GPUs under ideal circumstances: In two iterations of the same laptop. The cards were both paired with AMD's Ryzen 9 9955HX CPU, which removes a lot of the usual benchmarking discrepancy you'd run into in laptops. When both are installed in similar systems, we can get a good feel of how each card performs without external factors, and that is the case in these benchmarks.

Read more
Laptop GPU names feel like a scam
Gamer playing Overwatch on GIGABYTE G6X gaming laptop from GIGABYTE gaming laptop deals.

Despite the top-tier graphics cards from the past few generations being absolute power hogs, drawing hundreds upon hundreds of watts to deliver what feels like increasingly-modest performance gains, their laptop counterparts have taken enormous leaps in capabilities. AMD, Nvidia, and Intel have made great strides in what onboard graphics and dedicated graphics chips can do with relatively limited power and cooling options.

But even so, mobile GPU naming feels like a scam. The latest example is the flagship Nvidia RTX 50 GPU of this generation, the RTX 5090. On desktop it's about 30% faster than an RTX 4090, but with boatloads more memory, support for the latest multi frame generation technology, and a near-600W TDP to go with it.

Read more
Would you pay less for a defective GPU?
The RTX 5090 sitting on top of the RTX 4080.

The graphics card market is an absolute mess at the moment. Stock issues persist despite Nvidia's early claims that it would solve early issues with the 50-series, and AMD has promised to get its exceedingly popular RX 9000-series GPUs back in stock as soon as possible. That's meant pricing is even more ridiculous than ever, with top cards going for hundreds or even thousands of dollars more than they should, and last-generation options priced just as crazily.

But there are alternatives. Alongside buying older and second-hand cards, there's a new brand of GPU available at discounted prices for anyone willing to take a loss on maximum performance: Defective GPUs.

Read more