Skip to content
a nudge in the right direction

Review: Nvidia’s RTX 4070 Ti Super is better, but I still don’t know who it’s for

Card that was once the "4080 12GB" still occupies an awkward spot in the lineup.

Andrew Cunningham | 58
The 12VHPWR connector on PNY's RTX 4070 Ti Super. Credit: Andrew Cunningham
The 12VHPWR connector on PNY's RTX 4070 Ti Super. Credit: Andrew Cunningham
Our specific RTX 4070 Ti Super is a PNY model, the RTX 4070 Ti Super 16GB Verto.
The typical port arrangement.

Of all of Nvidia's current-generation GPU launches, there hasn't been one that's been quite as weird as the case of the "GeForce RTX 4080 12GB."

It was the third and slowest of the graphics cards Nvidia announced at the onset of the RTX 40-series, and at first blush it just sounded like a version of the second-fastest RTX 4080 but with less RAM. But spec sheets and Nvidia's own performance estimates showed that there was a deceptively huge performance gap between the two 4080 cards, enough that calling them both "4080" could have lead to confusion and upset among buyers.

Taking the hint, Nvidia reversed course, "unlaunching" the 4080 12GB because it was "not named right." This decision came late enough in the launch process that a whole bunch of existing packaging had to be trashed and that new BIOSes with new GPU names needed to be flashed to the cards before they could be sold.

The end result of all this rigamarole was the GeForce 4070 Ti, a card that certainly performed well against the previous-generation RTX 3070 Ti but still came with a big generational price jump from $599 to $799. It was too expensive to be a mainstream or "budget" card by any stretch of the imagination, but not fast enough to be a definitive cut above older RTX 30-series GPUs like the 4090 and 4080 had been.

This week Nvidia is launching the cumbersomely named GeForce RTX 4070 Ti Super, as a sort of mid-generation correction to the original card—the original 4070 Ti is being discontinued, rather than getting a new price tag à la the non-Super RTX 4070. The 4070 Ti Super is definitely faster than the old one at the same $799 price, which we'd still call a good thing. But that's still a high price in the end, and stronger-than-usual competition from AMD ultimately helps to make the 4070 Ti Super one of the less-compelling GPU options in the RTX 40-series lineup.

Meet the 4070 Ti Super

RTX 4090 RTX 4080 RTX 4080 Super RTX 4070 Ti RTX 4070 Ti Super RTX 4070 RTX 4070 Super
CUDA Cores 16,384 9,728 10,240 7,680 8,448 5,888 7,168
Boost Clock 2,520 MHz 2,505 MHz 2,550 MHz 2,610 MHz 2,610 MHz 2,475 MHz 2,475 MHz
Memory Bus Width 384-bit 256-bit 256-bit 192-bit 256-bit 192-bit 192-bit
Memory Clock 1,313 MHz 1,400 MHz 1,437 MHz 1,313 MHz 1,313 MHz 1,313 MHz 1,313 MHz
Memory size 24GB GDDR6X 16GB GDDR6X 16GB GDDR6X 12GB GDDR6X 16GB GDDR6X 12GB GDDR6X 12GB GDDR6X
TGP 450 W 320 W 320 W 285 W 285 W 200 W 220 W

The 4070 Super got its speed upgrades from a bunch of extra CUDA cores, and the 4070 Ti Super gets some of those, too—a 10 percent increase from the regular 4070 Ti. But the memory subsystem also gets healthy upgrades, jumping from 12GB of memory to a more future-proof 16GB and, accordingly, increasing the width of the memory bus from 192 bits to 256 bits.

That second thing has been a bit of a sore spot for enthusiasts for the entire RTX 40-series—memory bus widths across the lineup are generally narrower than they were for 30- and 20-series cards in the same tier. Nvidia says that the addition of extra cache memory in the 40-series helps to make up for this, but there's still been grumbling about how less memory bandwidth is limiting these cards' performance. Occasionally, especially in the case of the 4060 Ti, there has been pretty solid evidence of performance issues at higher resolutions, where some cards’ relative performance goes down as resolution scales up.

Like most OEM cards, Nvidia's partners tend toward large triple-fan designs most of the time. Unlike other RTX cards, Nvidia doesn't make a Founders Edition version of the 4070 Ti Super. PNY's card is pictured here next to a regular 4070 Super.
Like most OEM cards, Nvidia's partners tend toward large triple-fan designs most of the time. Unlike other RTX cards, Nvidia doesn't make a Founders Edition version of the 4070 Ti Super. PNY's card is pictured here next to a regular 4070 Super. Credit: Andrew Cunningham

These upgrades don't bring the 4070 Ti Super up to the level of the original 4080, which is a sign of just how off-base the "4080" label would have been for the original GPU. But they get it quite a bit closer. They also don't increase Nvidia's stated power consumption specs for the card, which stay level at 285 W; we noticed a slight uptick in power consumption, but this could just be variance between different OEMs' specific settings. Our 4070 Ti was from MSI, and the 4070 Ti Super was the PNY GeForce RTX 4070 Ti Super 16GB Verto; PNY's card comes with a 30 MHz game clock boost and 15 MHz boost clock boost, a barely noticeable increase that is typical of manufacturer overclocks.

Performance

Gaming testbed
CPU AMD Ryzen 7 7800X3D (provided by AMD)
Motherboard ASRock X670E Taichi (provided by AMD)
RAM 32GB (2x16GB) G.Skill Trident Z5 Neo (provided by AMD), running at DDR5-6000
SSD Western Digital Black SN850 1TB (provided by Western Digital)
Power supply EVGA Supernova 850 P6 (provided by EVGA)
CPU cooler 280 mm Corsair iCure H115i Elite Capellix AIO
Case Lian Li O11 Air Mini
OS Windows 11 22H2 with Core Isolation on, Memory Integrity off
Drivers Nvidia RTX 4070 Super and 3080 Ti: Pre-release driver 546.52
Nvidia RTX 4070 Ti and 4070 Ti Super: Pre-release driver 551.15
Other Nvidia cards: 536.99 (8/8/2023)
AMD RX 7800 XT: Pre-release driver 23.20.01.05
AMD RX 7900 XT: Adrenalin 23.8.1

Whether you're impressed or not by the 4070 Ti Super's upgrades depends on what you want to use it for. If you're playing at 4K, the extra CUDA cores and the extra memory bandwidth both contribute to some respectable increases, usually in the 12 percent range for non-ray-traced games and the 7 percent range for the ray-traced ones (the one exception is Cyberpunk 2077, which at 4K with ray tracing on saw its average frame rates jump up a disproportionate 36 percent).

At 1440p, because the old 4070 Ti's 192-bit memory interface was less of an issue, the performance gains are less impressive. You're looking at somewhere between a 5 and 10 percent increase in average frame rates across the games we tested.

In either case, the 4070 Ti Super is not as big an upgrade over the original as the 4070 Super was to the original 4070. And, at least in the tests we ran, there was no readily visible direct benefit to the jump from 12GB of RAM to 16GB, though this may well change by the time the 4070 Ti Super is a couple of years older and games have gotten a couple of years more graphically complex. The extra memory will also benefit memory-intensive GPU computing and running AI workloads. AMD continues to offer more memory than Nvidia across most of the RX 7000-series lineup (the 7900 XT comes with 20GB, and the $329 7600 XT and $500-ish 7800 XT both come with 16GB), but 16 still feels pretty reasonable for a card like this, a high-end but not top-end GPU.

Meanwhile, AMD continues to do what it has been content to do this entire generation—undercutting Nvidia a little, but not comprehensively. The Radeon 7900XT is the card to look at here, currently hovering around a street price of $750 and beating the 4070 Ti Super across the board in all of our non-ray-traced 4K benchmarks.

As usual, the script flips when you turn ray-tracing on in most games, but even then, Cyberpunk is the only game where the 4070 Ti Super truly blows the 7900 XT out of the water. The 7900 XT can keep up in Forza—the least demanding of our ray-traced tests—and manages to come within a few frames per second in Returnal. Also, surprisingly, AMD's power efficiency holds up pretty well next to Nvidia's here, using around 9 percent more power in our tests while performing between 2 and 29 percent better at 4K in our non-ray-traced benchmarks.

Credit: Andrew Cunningham

Obviously, how the cards stack up to each other is heavily dependent on the games you're playing and the settings you're using. And AMD still doesn't offer DLSS upscaling or other less-tangible Nvidia-specific benefits. But the 7900 XT is a pretty strong argument against the 4070 Ti Super, even better than the RX 7800 XT compared to the RTX 4070 Super or the RX 7600 compared to the RTX 4060.

Better, but still meh

The 12VHPWR connector on PNY's RTX 4070 Ti Super.
The 12VHPWR connector on PNY's RTX 4070 Ti Super. Credit: Andrew Cunningham

Is the 4070 Ti Super a good value? It depends on how you want to look at it. These speed increases make it a solid improvement from the highest-end RTX 30-series cards, for less money than the highest-end RTX 30-series cards. It's faster than the regular 4070 Ti and offers more memory at the exact same price, theoretically helping future-proof it against creeping video RAM requirements.

But by most metrics, the 4070 Ti was one of the least compelling cards in the 40-series lineup, and while the 4070 Ti Super is better in important ways, it's not better enough to really change that. It's 33 percent more expensive than the 4070 Super, and while its extra memory bandwidth, RAM, and CUDA cores help the 4070 Ti Super pull away from the 4070 Super in 4K games with heavy ray-tracing effects, the gap between them is often only about 20 percent, sometimes even less. At the same time, AMD's Radeon 7900 XT manages to put up a very good fight, offering better performance in most cases for less money and with not-disproportionately higher power use.

Ultimately, I have a hard time conjuring up the kind of person I'd recommend the 4070 Ti to. Sticking just to Nvidia's lineup, for the sake of argument: The 4060 is a good default recommendation if you just want a cheap card that will make most games playable; the 4070 Super is the way to go if you're after a cost-efficient card to go with a new high-refresh-rate 1440p monitor, or you want a slightly more future-proofed system without totally blowing your budget. The 4090 is the one to get if you want to put performance above all else, since there's nothing else that can really touch it (though we'll see how the 4080 Super changes things).

The 4070 Ti Super just ends up floating in between a couple of different categories, nowhere near cheap enough for a budget or midrange build, and not quite fast enough for a pull-out-all-the-stops build. Even after being renamed and getting its specs overhauled, the 4070 Ti still feels like an awkward fit.

The good

  • Usually 5–12 percent faster than the 4070 Ti at the same price
  • Particularly good improvements at 4K, thanks to some combination of more RAM and wider memory bus
  • Power consumption goes up very little compared to the 4070 Ti
  • Faster than much more expensive (at the time) RTX 30-series cards
  • The standard fringe benefits of Nvidia cards: DLSS upscaling, DLSS Frame Generation, good software support for GPU computing/AI apps

The bad

  • Still pretty expensive, historically speaking
  • AMD's RX 7900 XT makes a very strong argument for itself, for a bit less money
  • Minor performance upgrades at 1440p

The ugly

  • Neither a good enough value nor a fast enough card to stand out from the crowd
Photo of Andrew Cunningham
Andrew Cunningham Senior Technology Reporter
Andrew is a Senior Technology Reporter at Ars Technica, with a focus on consumer tech including computer hardware and in-depth reviews of operating systems like Windows and macOS. Andrew lives in Philadelphia and co-hosts a weekly book podcast called Overdue.
58 Comments