As expected, Nvidia is moving ahead with the launch of a 12 GB version of its famous RTX 3080 graphics card, which is 2 GB more than the previous version. Nvidia has slightly increased other specs as well, so it’s not just a simple ‘put some more memory on that bad boy’ scenario, but such a modest upgrade to an existing model is rare in the world. the world of GPUs. And just like with previous pandemic launches, it comes with the asterisk that most people won’t even be able to buy one, even if they’re willing to pay an inflated MSRP for it, making it quite another. GPU launch that arouses more sadness than jubilation. On a related note, good luck finding a review for it, as it looks like Nvidia didn’t allow any press reviews on Day 1, not even from its partners, but more on that later.
Despite this austere introduction, the specs of the new GPU (for the most part) look good on paper, thanks to its small but significant upgrades. The move to 12GB should help the card run high-resolution AAA games that only need a little more RAM than 10GB, either to handle future high-resolution games or to juggle the demands of Rasterization and ray tracing VRAM simultaneously. It was a bit odd for Nvidia to keep the RTX 3080 to only 10GB of VRAM at launch given how long the GPUs stayed at or near 8GB. The increased costs of GDDR6X and limited availability would have been reported. impacted Ampère’s VRAM loadings since its launch.
Nvidia opened up the pipe a bit, upgrading the memory bus from the 320-bit card in the previous model to 384-bit like the rest of its flagship cards. This is a significant upgrade, providing 19% more memory bandwidth from 760 GB / s to 920 GB / s. Nvidia also slightly increased CUDA cores, from 8,704 to 8,960. That’s an increase of about three percent.
Clock speeds have also received a boost. The base clock increases by 180 MHz and the boost clock increases by 40 MHz. The base clock increase is substantial, but there are many factors that govern clock speed while gaming. The base clock improves by 14%, but the boost clock only increases by 2%. The 12GB gain of the RTX 3080 over the 10GB RTX 3080 will depend on which clock enhancement has the most impact on real-world gaming.
All of these moderate changes increased the power requirements of the board from 320W to 350W. It’s the same as the RTX 3080 Ti.
Nvidia’s website lists both the OG 3080 and the new variant, but it’s unclear whether it will sell a founder’s edition of the card, or at what price. Regardless, the 12GB model has started showing up on several of the company’s partner sites, including EVGA which has a landing page for that. The company offers two versions: a triple-slot super-thic FTW version for $ 1,299 and a dual-slot XC3 Ultra for $ 1,249. The chonky FTW card requires three 8-pin PCIe power connectors, which is unchanged from the previous model. Galax is also promoting its new GPU on Twitter, with the unintentionally funny nickname “Ex-player.“Seriously Galax, at these prices we could all be former players for too long.
Overall, the new RTX 3080 12GB is a slight upgrade. We’ll have to wait and see if the extra memory and extra bandwidth will lead to any big gains in high-res games, especially ray tracing. The underlying problem is that the GPU at the heart of the card also needs to be able to deliver the necessary performance that this extra memory could unlock.
For example, last year Nvidia released an RTX 3060 GPU with 12GB of RAM to compete with the 12GB of AMD 6700 XT, but no one would say these cards can drive AAA games on a 4K panel with ray tracing. . However, on the RTX 3080 this might be possible in some titles. Maybe giving it a little more RAM will give the 3080 the performance it should have had at launch so long ago.
Finally, when it comes to the reviews of the map, here’s where things get weird. According to TechSpot, Nvidia sampled them a card to be ready for launch day, which is today, but didn’t give them a beta driver to actually test the card. Later in the process, they were told that there would be no driver at all, so instead they would have to wait for the card to release and then just download the publicly available driver. This means that all examiners with GPUs in hand will download the driver today and start their testing, delaying exams by at least several days, assuming there are no issues with testing, etc. This means that Nvidia specifically didn’t want the reviews posted before people could consider purchasing the card, which is very odd.
TechSpot translates this “shady” behavior into Nvidia wanting to avoid the bad press that will likely accompany reviews, as the launch of this card can easily be seen as a simple “price correction” for the original card.
As you will recall, in the midst of the pandemic when the RTX 3080 was officially launched, people were shocked at the relatively affordable price of $ 699, but as we found out these cards barely existed. Nvidia itself stopped selling them on its website due to overwhelming demand and shifted that responsibility to Best Buy, causing gamers to use the F5 button on their keyboards in hopes of finding some. one in stock. All this to say that every launch since then has encountered instant out of stock notifications, scalpers and bots buying every card for sale, and lots of pissed off gamers.
Nvidia appears to be trying to avoid that same wave of bad press this time around, or at least avoid it long enough to sell some cards in the channel before the inevitable happens. We didn’t ask Nvidia to comment on this, but searching the web there are indeed no reviews on the card, despite officially launching today. Obviously, Nvidia knows that it will sell every one of them, at the price it dictates, regardless of the medical coverage, good or bad. Obviously, no one will be able to find this card in stock anywhere, which was the same situation when it was last launched: a 12GB version of the RTX 2060.
This brings us to the number one gamer issue with Nvidia right now – putting your money into making more existing cards instead of launching new, more expensive cards. We do know, however, that Nvidia can’t just snap its fingers and triple production, and to its credit the company has publicly stated that it is investing billions of dollars in securing the supplies it needs to grow and sustain. its production, but this situation will take time to resolve. Its CFO recently said help could arrive, but not until the second half of 2022.
- PCI Express Bandwidth Test: PCIe 4.0 vs. PCIe 3.0 Gaming Performance & Limited VRAM Memory Buffers
- No more VRAM, but for whom? Nvidia RTX 2060 12 GB review
- Nvidia Reportedly Prepping Two New RTX 3050s, One with Just 4GB of VRAM
- AMD hides its claim that 4 GB of VRAM is not enough, just as it launches a 4 GB GPU
- RTX 4090 to Offer 24GB GDDR6X VRAM, RTX 4080, 4070 Detailed