Digital Trends may earn a commission when you buy through links on our site.

AMD Radeon VII vs. Nvidia RTX 2080

Nvidia’s RTX graphics cards are everywhere you look, whether it’s in desktops or laptops. Ray tracing controversies aside, they’re powerful cards. But now, AMD has an answer.

The AMD Radeon VII is a true successor to the Vega 64 in more ways than one. It’s built on the second-generation, 7nm Vega architecture, and it’s the first high-end graphics card AMD has released since its Vega predecessor. There’s no question that it’s more powerful than that card, but how does it fare against its main competition?

We pitted the AMD Radeon VII versus the Nvidia RTX 2080 to find out.


RTX 2080
Riley Young/Digital Trends

AMD’s Radeon VII might be a successor Vega architecture, but its design is quite different than its predecessor. The 7nm process makes the GPU itself smaller and facilitates a shrinking of the whole die from 495mm² on the Vega 64, to 331mm² with the Radeon VII. It’s fitted with four stacks of second-generation high bandwidth memory (HBM2) and runs at a much higher frequency than the first-generation Vega cards.

Nvidia’s RTX 2080 is built on Nvidia’s new Turing architecture and is paired with GDDR6 memory that runs at a higher speed than the 10-Series Pascal graphics cards. Turing cards improve performance over their last-generation counterparts by increasing the number of CUDA cores and memory speed. Clock speeds remain much the same when running at stock, though automated 20-Series overclocking does aid performance.

Nvidia and AMD use different designs in their graphics cards manufacturing, so the specifications aren’t necessarily directly comparable, but here they are nonetheless:

AMD Radeon VII Nvidia RTX 2080
Architecture Vega 20 Turing
Node process 7nm 12nm
Die size 331mm² 545mm²
Transistor count 13.2 billion 13.6 billion
Processor cores 3,840 stream processors 2,944 CUDA cores
Base clock 1,400MHz 1,515MHz
Boost clock 1,750MHz 1,710MHz
Memory 16GB HBM2 8GB GDDR6
Memory interface 4,096-bit 256-bit
Memory bandwidth 1,000GB/s 448GB/s
TDP 300w 250w
Price $700 $700

To see how these cards performed head to head, we fitted them to our gaming test bench that’s running an AMD Threadipper 1950X (in game mode) and 32GB of memory. In each case, we ran the latest drivers that were available at the time, though do keep in mind that the Radeon VII drivers are technically still pre-release versions.

In 3DMark Fire Strike, the results were impressive for both cards, but noticeably more so for the Radeon VII. AMD’s new card was expected to perform better against Nvidia’s GPUs at higher resolutions, but in the base Fire Strike test, it not only beat out the RTX 2080 but performed comparatively well to the RTX 2080 Ti, a much more expensive GPU.

In gaming benchmarks we saw similar results at 1080P, with the Radeon VII delivering frame rates in Battlefield V at both medium and Ultra settings well above 100 FPS, beating out not only the RTX 2080 but the 2080 Ti as well. The always-taxing Deus Ex: Mankind Divided proved more challenging, but the Radeon VII still pulled ahead of the 2080 and 2080 Ti with an average 90 FPS when on High, and 86 FPS on Ultra settings.

At 1440p, the 2080 Ti takes its rightful place at the head of the pack, but Radeon VII takes an even greater lead over the 2080 and makes its predecessor, the Vega 64, look very much like the last-generation card it is.

When we increase resolutions to 4K, all of the cards struggle to maintain 60+ FPS in Battlefield V. Only the 2080 Ti manages it in Deus: Ex at Medium settings, but the Radeon VII remains out in front of the 2080 in all cases.


Ray tracing ultra — Screenshot 5

As powerful as Nvidia’s RTX graphics cards are, Nvidia spent much of the launch event talking about new features rather than performance. Ray tracing and deep learning super sampling (DLSS) — made possible with onboard RT and Tensor cores, respectively —  were big news. While in early 2020 they still weren’t supported by many games, the numbers continue to grow. In some cases, they can have a dramatic impact on games.

Ray tracing makes certain games look prettier, albeit with a big performance cost, and DLSS shows signs of making games both look better and run faster.

Although AMD does have functioning ray tracing in the form of Radeon Rays using the Vulkan API, that’s not a technology that is implemented in any games at this time, and AMD hasn’t made it viable with the Radeon VII. Nor is DLSS available, though AMD has suggested that its cards’ general compute units are capable of something similar. Furthermore, it may even implement it in the future using Microsoft’s open standard, DirectML.

Both cards support different frame syncing technologies out of the box. Nvidia’s RTX 2080 supports its bespoke G-Sync which is only available on compatible monitors. AMD’s Radeon VII supports FreeSync and FreeSync 2, which are only available on compatible monitors, though they do tend to be cheaper and more plentiful than their G-Sync counterparts.

Both cards support the full gamut of gaming APIs including DirectX11, DirectX12, OpenGL, and Vulkan.

Nvidia’s RTX 2080 also supports SLI via NVLink for multiple GPUs. AMD has said that it doesn’t plan to offer its traditional multi-GPU technology, Crossfire, with the Radeon VII. However, both Vulkan and DirectX12 have support for multiple graphics cards as an open standard known as MGPU, so it may be that if supported by games (like Strange Brigade), two Radeon VII cards could be run in tandem using that technology.

Compatibility & Price

AMD Radeon VII
Riley Young/Digital Trends

Nvidia’s RTX 2080 launched with a Founders Edition priced at $800 but has since seen the release of more affordable third-party alternatives. Today those range in price from $700 to around $900 depending on the cooling options and aftermarket features. These can often be found with a free game or two.

The AMD Radeon VII launched with a price tag of $700, but as it is now end of life, it’s hard to find anywhere at anything close to reasonable. AMD originally offered three free games — Resident Evil 2, The Division 2, and Devil May Cry 5 — as part of its Raise the Game promotion, but that has concluded.

When it comes to compatibility, you’ll want a motherboard that supports PCI-Express 3.0 x16 to take full advantage of both cards. If your system has a PCI-Express 2.0 x16 or PCI-Express 3.0 x8 slot instead, both cards should still work, but you may see a small performance lapse due to bottlenecking.

Power requirements for these cards are reasonably steep, but the Nvidia GPU isn’t quite as demanding. It requires around 250 watts of power and cooling potential when in use, while the Radeon VII is rated at 300 watts. You want at least a 600-watt PSU if you’re running the RTX 2080 or a 700-watt for the Radeon VII.

AMD raises its game

AMD Radeon VII
It’s been a long time since AMD legitimately competed with Nvidia at the top end of the graphics card market. The Radeon VII isn’t quite strong enough to be a direct competitor for the likes of the RTX 2080 Ti, especially at higher resolutions, but it’s not far off that. At a $700 asking price it’s costed competitively enough with the RTX 2080 that Nvidia raised its game in 2019 to stay ahead. We’ll get to that in a moment.

Our testing isn’t exhaustive, but it suggests that the Radeon VII will be a more capable card than the RTX 2080 in a number of games and at most resolutions and detail settings. It may be a little more power-hungry, but the newly shrunk GPU and the massive amount of high-speed memory make it one of the most exciting graphics cards available today.

Although AMD hasn’t made it official, reports claimed in August 2019, that the Radeon VII had already reached its end of life. AMD’s “Big Navi” GPU built on the 7nm+ process node and its RDNA 2 architecture will likely take its place when it arrives later this year. As it stands now, the current Radeon VII stock is minimum at best, now mostly appearing in desktop configurations for workstation machines.

Nvidia strikes back

Not content with its RTX 20-Series family and the cool new features it brought to PC gaming, Nvidia introduced its RTX 20-Series SUPER cards in July 2019. The company said these cards would increase performance by up to 25% over the non-SUPER cards thanks to improvements to the Turing architecture. The new family includes the RTX 2060 SUPER, the RTX 2070 SUPER, and the RTX 2080 SUPER.

But Nvidia’s onslaught doesn’t stop there. Nvidia just revealed its next-generation Ampere GPU architecture, though the first implementations will reside in chips for servers and workstations along with the DGX A100 for A.I.-based workloads. Nvidia’s RTX 30-Series based on consumer-level Ampere GPUs isn’t expected to arrive until later this year.

That all said, we’re anxious to see how the RTX 3080 and the Radeon VII successor will duke it out in terms of performance and pricing.

Editors' Recommendations