Skip to main content

Nvidia GeForce RTX 2080 vs. RTX 2080 Ti

Riley Young / Digital Trends

Boasting up to six times the performance of the older GTX 1080 series graphics card, Nvidia’s latest GeForce RTX 2080 and RTX 2080 Ti are GPU beasts. Even though you may not need — or experience — such massive performance gains on current titles, enthusiasts eyeing the new RTX cards are actually buying into Nvidia’s vision for the future of gaming, which is centered around the new ray tracing capabilities of the RTX chips’ Turing architecture.

But even at the high end of Nvidia’s new gaming GPU line, there is a sizable difference in what the standard RTX 2080 Founders Edition is capable of compared to the RTX 2080 Ti Founders Edition. Some will likely want to gravitate towards the Ti’s improved specifications, but that comes with a hefty $400 price premium. We’ll break down just how the two top-shelf RTX GPUs stack up.

Recommended Videos

Performance

Image used with permission by copyright holder

Because it’s more densely packed, the RTX 2080 Ti Founders Edition performs slightly better in our early benchmarks compared to its non-Ti variant. That’s to be expected, given that the Ti packs in more CUDA, Tensor, and RT Cores.

Get your weekly teardown of the tech behind PC gaming
Check your inbox!

When benchmarked using 3DMark, the RTX 2080 Ti performed consistently better across the three tests. This means that the Ti variant had a performance improvement over the base model ranging from 13 percent for the Fire Strike test to up to 31 percent for the Sky Diver test.

When we looked at our gaming results using Deus Ex: Mankind Divided, performance between the two high-end RTX chips were on par at lower resolutions, but the difference was significant at 4K resolution. On Ultra, both chips posted the same results at 1080p, and the Ti variant started to edge ahead under 1440p. Under 4K resolution, the RTX 2080 Ti outperformed the standard model by 29 percent, suggesting that the added Cuda cores and memory on the Ti variant make a more meaningful contribution to graphics performance at higher resolutions and during more GPU-intensive tasks.

Interestingly, though, performance between the RTX 2080 Ti and the RTX 2080 was roughly on par using our Civilization VI test. With the 4K Ultra settings enabled, the Ti variant scored 74, compared to 76 on the non-Ti chip. Performance was similar using the 4K Medium, 1440p Ultra, and 1440p Medium settings, with both chips posting results within range of each other.

Both the RTX 2080 Ti and RTX 2080 will be able to handle first-person shooters at 4K resolution and 60 frames-per-second. And as we’ve seen demonstrated by the Deus Ex: Mankind Divided results, games with Deep Learning Super Sampling (DLSS) built-in should see even bigger performance gains with the Ti version of the RTX 2080.

DLSS delivers better image quality improvements, smoother frames, and better anti-aliasing, thanks to the use of the the built-in Tensor cores and artificial intelligence. The Ti version of the the card has 576 Tensor Cores, versus just 384 on the non-Ti variant, giving it a bigger performance advantage in situations where the GPU would be taxed. In this case, some of these dedicated cores kick in to offload some of the strain on the GPU.

Features

RTX 2080 Ti RTX 2080
CUDA cores: 4,352 2,944
Base speed: 1,350MHz 1,515MHz
Boost speed: 1,545MHz 1,710MHz
Boost speed (FE model): 1,635MHz 1,800MHz
Memory (GDDR6): 11GB 8GB
Memory speed: 14Gbps 14Gbps
Memory interface: 352-bit 256-bit

At the top of Nvidia’s graphics pyramid, both the RTX 2080 Founders Edition and RTX 2080 Ti Founders Edition support ray tracing, AI-enhanced image rendering, and the single-cable VRLink protocol to connect virtual reality headsets to PCs using a single USB-C cable.

The main difference between these two cards is in the number of dedicated Cuda, Tensor, and RT Cores. The Ti’s more densely packed cores gives it a performance advantage under some tests. The Ti version comes with six graphics processing clusters, each with its own raster engine and six texture processing clusters. Each texture processing cluster comes with two streaming multiprocessor (SM), with each SM containing a single RT processing core, 64 CUDA Cores, eight Tensor Cores, and four texture units. Essentially, as you go down the line in the RTX series, you’ll find fewer RT and Tensor Cores. The RTX 2080, for example, packs just 46 RT cores and 368 Tensor Cores, compared to 72 RT cores and 576 Tensor Cores on the Ti edition.

With more RAM —  11GB versus 8GB — and the ability to handle more operations per second, the Ti card should also perform better than the base RTX 2080 when it comes to ray tracing. Nvidia claims that the RTX 2080 is capable of 60 trillion RTX OPS and 8 GigRays per second, while the more capable Ti edition can handle 78 trillion RTX OPS and 10 GigaRays per second.

Given that there are no game available right now with ray tracing, we’re not able to get benchmark results for these cards. Once ray tracing hits, we can likely expect better performance in how light is rendered in real-time a scene with the RTX 2080 Ti due to its stronger hardware specs.

Which to buy?

Image used with permission by copyright holder

The Founders Edition of the RTX 2080 and RTX 2080 Ti are the top two Nvidia’s new line cards, but they’re also the two most expensive. The RTX 2080 Founders Edition retails for $800, while the Ti edition will cost $1,200. If you’re looking to connect two cards together, Nvidia’s Founders Edition cards use the NVLink connector, so you’ll need to add a $80 bridge for a multi-GPU setup.

Unless you’re pushing the performance boundaries with high resolution gaming, most gamers will likely experience little perceivable performance improvements with the Ti card at this time. Given the steep price premium of $400 between the two cards, you may be better served by spending the difference in cost in upgrading your SSD or system RAM, or even going springing for a previous-gen GTX 1080 or 10 80 Ti. That is, at least until more ray tracing games launch to justify this investment. Ray tracing and AI-enabled rendering may be the future, but that future isn’t quite here yet.

Chuong Nguyen
Silicon Valley-based technology reporter and Giants baseball fan who splits his time between Northern California and Southern…
Want an RTX 5090? Prepare to wait a little longer
RTX 4090.

Nvidia's upcoming top GPU is taking its sweet time to make it to the market, and by the sound of it, we won't see it anytime soon. According to a new report from Benchlife, as well as various other sources, Nvidia is planning to unveil the RTX 50-series at CES 2025 in January. This means that the RTX 5090 is unlikely to make an appearance any sooner than three to four months from now. On the upside, we just learned even more about what the card's going to offer.

After a few months of managing expectations, many GPU enthusiasts no longer expect the RTX 50-series to be released this year -- and leakers agree. Following the huge specification leak we got yesterday, at least two new publications (both Benchlife and The Verge) are now claiming that Nvidia won't announce its next-gen GPUs until 2025. Reputable hardware leakers like kopite7kimi have also previously said that early 2025 is the current target.

Read more
Nvidia is reportedly sunsetting the RTX 4090
The RTX 4090 sitting alongside the Fractal Terra case.

The RTX 4090 is undoubtedly the best graphics card you can buy right now from a performance standpoint, but Nvidia is reportedly discontinuing the flagship GPU. Reports from the Board Channel forums (shared by Wccftech) suggest Nvidia is preparing to end production of the RTX 4090 and the China-exclusive RTX 4090D starting next month in order to make way for next-gen RTX 50-series graphics cards.

It's not surprising that Nvidia would wind down production of the RTX 4090 as the next generation of graphics cards approaches. Flagship GPUs like the RTX 4090 don't have much of a shelf life after a new generation has released, which is something we saw in action with the RTX 3090. Although Nvidia could end production of the GPU in October (the company itself hasn't, and likely won't, confirm that detail publicly), the card won't immediately disappear from store shelves.

Read more
Wait, what? Nvidia’s RTX 50-series might be ready to go this month
RTX 4090.

Update: According to MEGAsizeGPU on X (formerly Twitter), the following might be a mistranslation. The source reportedly talks about Nvidia finalizing the design for Blackwell in September instead of launching the card. No details about the release date have been confirmed. The original article follows below.

Nvidia's RTX 50-series graphics cards are coming -- we know that for a fact. But when? The release dates of these graphics cards have been the topic of much speculation. Early leakers predicted that they'd launch in late 2024, but the general consensus slowly shifted toward an early 2025 release instead.

Read more