Nvidia GeForce RTX 4080 16GB Founders Edition – Photo
What’s in a name
Before we get to the specs and performance numbers, we should cover the naming kerfuffle of the RTX 4080 and talk a bit about how Nvidia’s GPUs are generally positioned and why this generation is slightly different than in previous years. Dating back more than a decade, Nvidia GPUs with the nickname “-80” are considered the flagship main cards and are priced between $ 500 and $ 700. Looking more specifically at recent trends, the GTX 1080 has been launched. at $ 599 and both the RTX 2080 and 3080 launched at $ 699.
You may be wondering, then, why the RTX 4080 starts at nearly double that range. The answer is in that aforementioned naming fiasco. Initially, Nvidia had two variants of the RTX 4080: a 16GB for $ 1,199 (the version we’re reviewing here) and a 12GB, priced at $ 899. This wouldn’t be the first time Nvidia has launched cards. with VRAM variants, but typically the amount of VRAM was the only difference, while in this case the two cards also had different core counts and clock speeds, differences that previously would have warranted a move to another level (in this case case, the RTX 4070).
People rightly complained about the confusion this was already starting to cause and, to Nvidia’s credit, responded by opting to “unlock” the 12GB RTX 4080; now it is rumored that those cards will be announced again under the name “RTX 4070 Ti”, although nothing is official at the moment.
That’s all well and good, but it still leaves us with a “mainstream” card with the enthusiastic level price that previously would have been reserved for a card with the “Ti” label, representing a middle generation pass. In other words, typical generational comparisons are a bit skewed this time around, so we’ll mostly be comparing the RTX 4080 to the RTX 3080 Ti, which also launched at $ 1,199 in June 2021, as opposed to the RTX 3080.
Nvidia GeForce RTX 4080 – Design and functionality
If you read my RTX 4090 review, you will remember that it is an absolutely huge card, both in terms of size and performance. The RTX 4080, meanwhile, is no longer small. It has the same triple slot designation, measures 11.9 inches (304mm) long, 5.4 inches (137mm) wide and 2.4 inches (61mm) thick, the exact same dimensions as the RTX 4090 . This is a great paper. For comparison, the RTX 3080 measured 11.2 inches (285 mm) in length, 4.4 inches (112 mm) in width and 1.5 inches (40 mm) in thickness, while the RTX 2080 and GTX 1080 were even smaller.
Most of that weight comes from the large biaxial flow-through cooling solution needed to keep temperatures in check. The cooler design is mostly similar to that of the RTX 3090, but with larger fans and taller fins to achieve what Nvidia says is 15% more airflow at the same noise level. In practice, the RTX 4080 remained quiet while maintaining temperatures around 53-55 ° C, peaking at 57 ° C, during a long benchmarking period.
Compared to the RTX 3080 Ti, the RTX 4080 has 9,728 CUDA cores (compared to 10,240), 304 fourth-generation Tensor cores (compared to 320 third-generation) and 76 third-generation RT cores (versus 80 second-generation). In other words: it has newer cores, but overall they are slightly inferior. The decrease in count shouldn’t be alarming though, since the 4080 includes a boost clock speed of 2,505 MHz compared to the 1,665 MHz clock of the RTX 3080 Ti, not to mention 16 GB of GDDR6X VRAM, compared to 12 GB. of its series 30 “predecessor.”
Like the RTX 4090, the 4080 uses the rather controversial 16-pin 12VHPWR power connector that has recently been in the news due to reports of overheating and melting. We did not encounter any problems in any of our tests, but we will certainly monitor the situation as this generation of graphics cards matures.
Speaking of power, the RTX 4080 has a TDP of 320W, down from the RTX 3080 Ti’s 350W. Nvidia recommends using a 750W power supply as a minimum. There is also a 3x 8 pin adapter in the box for people whose power supplies don’t have the new connector.
For ports, the RTX 4080 has 3 DisplayPort 1.4a and 1 HDMI 2.1a. This is the typical layout for the latest generation graphics cards, although AMD’s recently announced RX 7900 XT and XTX utilize the latest DisplayPort 2.1, which has more than triple the bandwidth and enables 4K resolution up to 480Hz. or 8K up to 165Hz, compared to 240Hz to 4K and 60Hz to 8K for DisplayPort 1.4. Most games and monitors won’t be able to take advantage of that bandwidth, so that’s sort of a moot point, but AMD technically has the edge.
Nvidia Geforce RTX 4080 – Performance
Starting with our synthetic benchmarks, the RTX 4080 comes out swinging in 3D Mark Fire Strike Ultra with a 17% improvement over the RTX 3090 Ti and a 28% improvement over AMD’s RX 3950 XT, the two best GPUs of the previous generation. , and a 35% increase over its generational-priced equivalent predecessor, the RTX 3080 Ti. As you’d expect, however, it’s noticeably lower than the RTX 4090, scoring 16,255 compared to the RTX 4090’s 21,872, which makes perfect sense given the card costs $ 400 more.
Moving on to Unigine Heaven, the RTX 4080 outperforms the RTX 3090 Ti and RX 6950 XT at 1080p and 1440p, but it actually falls short of both cards at 4K. Against the RTX 3080 Ti, however, it consistently wins with an advantage of 13% at 1080p, 14% at 1440p and a slight 4% at 4K.
Ray-traced synthetics are more dramatic. The RTX 4080 offers an average 28% increase over the RTX 3090 Ti in our three tests and, of course, absolutely demolishes the RX 6950 XT, which lacks the ray tracing cuts of Nvidia’s hardware. Comparing it to the 3080 Ti it offers even more impressive results, with an average improvement of 45% over that card.
Moving on to our gaming benchmarks, the RTX 4080 again has good visibility across all three tested resolutions. At this point our benchmark tests are basically CPU bound at 1080p, with the RTX 4080 pinging the meter alongside the more powerful RTX 4090. 1440p is relatively similar, with the card showing large gains over the last generation in tests that are not CPU bound. , and of course matching the best in the tests they are.
Nvidia GeForce RTX 4080 16GB Founders Edition – gaming benchmark
Given the high-end nature of this hardware, however, the real story is at 4K. (If you’re not gaming at 4K or higher resolutions, you shouldn’t be spending that much money on a GPU.) By slightly expanding our test suite, you can see that the RTX 4080 offers notable gains over the previous generation, with an average improvement in performance. 27% compared to the RTX 3090 Ti and 45% compared to the RTX 3080 Ti. Keep in mind that the latest of those cards launched at the same price of $ 1,199, while the first one had an MSRP of $ 2,000 when it launched earlier this year (although prices have now dropped to about that you should expect to pay for a fresh off the shelf RTX 4080).
These are impressive gains, but not quite out of the ordinary when you consider that this is a new graphics generation. Looking back on our RTX 3080 review, that card offered 50% to 70% improvements over its generational predecessor, the RTX 2080 Super. That’s not to say discarding the RTX 4080: 4K framerates well above 60fps in the most demanding games will raise eyebrows for a few years to come – I just think it’s important to remember that we’re talking high-end, if not level. keen prices here, so my expectations are sky high.
Finally, I want to talk about Nvidia’s new DLSS 3 frame generation technology. Check out my RTX 4090 review for a more in-depth explanation, but in short the GPU examines two sequential frames, calculates the difference between them, and then uses the AI to generate a frame between them. As with the RTX 4090, I tested DLSS 3 and frame generation in Cyberpunk 2077.
DLSS once again offered a dramatic improvement, taking the RTX 4080’s framerate up to 73 without frame generation and 108 with it. These are fantastic numbers for one of the most technically demanding games available on PC today – and remember, this benchmark runs at 4K with maximum settings and ray tracing enabled. The 30-series RTX cards, meanwhile, both receive fewer enhancements from DLSS and don’t have access to frame generation all at once.
Of course, DLSS 3 is still a new technology and game support is limited for the moment. That said, it’s steadily spreading across more games, including Microsoft Flight Simulator, A Plague Tale: Requiem, and Marvel’s Spider-Man Remastered. If support continues to grow as expected and the performance increase remains formidable, DLSS 3 will be the killer feature that makes upgrading to a 40 series card really worthwhile for high-resolution, high-framerate gaming.