Tuesday, April 15th 2025
NVIDIA Launches GeForce RTX 5060 Series, Beginning with RTX 5060 Ti This Week
NVIDIA today announced the GeForce RTX 5060 series, with a combined announcement of the GeForce RTX 5060, the GeForce RTX 5060 Ti 8 GB, and the RTX 5060 Ti 16 GB. The latter two will be available from tomorrow, 16th April, which is also when media reviews of the RTX 5060 Ti 16 GB and 8 GB go live. The RTX 5060, meanwhile, is expected to be launched in May. The RTX 5060 Ti introduces the new 5 nm "GB206" silicon, which the SKU maxes out. This chip features 36 streaming multiprocessors (SM) across 3 GPCs. These work out to 4,608 CUDA cores, 144 Tensor cores, 36 RT cores, 144 TMUs, and 48 ROPs. The chip features a 128-bit GDDR7 memory interface driving 8 GB of 16 GB of 28 Gbps (GDDR7-effective) memory for 448 GB/s of memory bandwidth, which is a 55% increase over the RTX 4060 Ti.
NVIDIA recommends the RTX 5060 Ti for maxed out 1080p gameplay, including with ray tracing, although we expect it to be unofficially capable of 1440p gameplay with fairly high settings and ray tracing. You get new features being introduced with the RTX 50-series, including Neural Rendering, and DLSS 4 Multi Frame Generation. NVIDIA is pricing the RTX 5060 Ti 8 GB at $375, and the 16 GB sibling about $50 higher, at $425, although these could be fairy tale pricing given the unpredictable world trade environment and scarcity profiteering by scalpers.
NVIDIA recommends the RTX 5060 Ti for maxed out 1080p gameplay, including with ray tracing, although we expect it to be unofficially capable of 1440p gameplay with fairly high settings and ray tracing. You get new features being introduced with the RTX 50-series, including Neural Rendering, and DLSS 4 Multi Frame Generation. NVIDIA is pricing the RTX 5060 Ti 8 GB at $375, and the 16 GB sibling about $50 higher, at $425, although these could be fairy tale pricing given the unpredictable world trade environment and scarcity profiteering by scalpers.

115 Comments on NVIDIA Launches GeForce RTX 5060 Series, Beginning with RTX 5060 Ti This Week
That doesn't make them right. It's just makes them look like amateurs that can't tell the backside from a hole in the ground.Scratch that, misunderstood context there. Just watched the video.What's right about it?
The benchmarks overwhelmingly show that this card isn't doing much better than a 3070 8GB. So honestly, where is the advantage of 16GB VS 8GB(hint there isn't one).
My 3080 is STILL beating out this card two full generations later.. The VRAM is not the issue.
I really wish people would quit parroting this "8GB is not enough" nonsense.
Sure, I don't think the performance difference is that noticeable (there's no reason to suggest there is one between both models anyway, not a 3050 6GB situation which wasn't even the VRAM's fault.), but its still shady. And weird. And that's what Linus is calling out (and he's not the only person calling this out, too, by the way, he's just one of the bigger voices.)
You'd think NVIDIA would let partners give reviewers the 8GB models too but they seemingly told them not too. Who knows why. But I (and many other people) are bothered by how weirdly shady it is. Luckily this isn't a 3050 6GB situation where the lower VRAM card is severely cutdown sneakily and stealth launched. But its just something that NVIDIA really has no reason to be doing.
I haven't watch the LTT video.It seemed like they were parroting the same train of though that JayzTwoCents has been on about.Edit: Just watched it. I hate to say it, but Linus made a few good points there.. Wow.. Didn't think I'd be saying THAT...
NVidia is really messing the bed on the whole of the 5000 series launch.
If you look at the graphs, only one of them show the 16GB version having anything more than a sliver of an advantage.
www.techpowerup.com/review/msi-geforce-rtx-5060-ti-gaming-16-gb/31.html
So LTT is in the camp of folks that have objectively looked at factual data and concluded properly then good on them.
To save you watching the video, here is what happens when it runs out of VRAM, especially on PCIe 3.0 systems which a lot of people who buy cards in this class will still be using. It affects PCIe 4.0 as well, just not always as much. Bit more than just a sliver of difference eh? The 8GB card is brought to its knees in situations the 16GB card isn't breaking a sweat.
Whatever their agenda, keeping Nvidia in check is an important role of journalists. If Nvidia had their way we'd all be paying $1000 for a 96-bit RTX 5030 with 4GB VRAM and Nvidia's low-texture AI upsampling. We need independent reviewers to discourage rampant false advertising and misleading information. A lot of what Nvidia have published as claims for the 50-series are borderline illegal in many countries outside the US. False advertising and misrepresetation even make headlines in the US because if it's blatant enough there will be lawsuits.
Market competition is good for consumers. An unfair playing field because shady business practices and marketing lies undermine the competitive market playing field is bad for you and me, without exception.
Also, I'm not responding to the rest of your post as I don't feel the need spend the next 3 hours of my time explaining why Steve Walton is full of crap and his testing methodology is so deeply flawed. IF everyone was getting the same numbers he's getting, he would have merit. But that's not happening and this is not the first time the numbers he produces have been wildly out of wack. HUB is NOT a reliable source of information. Stop quoting them.In this situation, yeah, that's what he's doing.Also true! It's absolutely vital!
Multiple different websites and YouTubers have produced similar results of 8GB cards collapsing in performance when VRAM is exceeded, where the 16GB card sails along unaffected. Yes, people can turn down some settings and mitigate the problem, but on a 16GB card you don't have to - that's the point. Pretending the two cards are all but identical in performance with nary a sliver between them is false.
Indiana Jones is another one.
www.computerbase.de/artikel/gaming/indiana-jones-und-der-grosse-kreis-benchmark-test.90500/seite-2
Example, someone who's testing is actually trustworthy;
There are very little differences between 8GB and 16GB in 1080p or 1440p.
I'll take TPU and JegsTV's numbers over HUB all day, any day, every day.
EDIT: It also helps that modern consoles have NVME storage, which should theoretically help offset a lack of system RAM if there's a need to hit a swap file. It's not ideal, but 5500MB/s is way better than the previous gen's SATA spinners.
Considering how things have been going so far, I suspect the 8GB cards will be very hard to find, especially near MSRP. AIBs will focus on 16GB RGB OC models with oversized coolers and sell them for 5070 prices. My cursory look at MicroCenter's SKUs supports that notion. They have 16 5060Ti SKUs, and only TWO of those are 8GB models. The highest price 5060 Ti is exactly 1 dollar less than the cheapest 5070. And it doesn't matter, as everything is sold out already. The 5060 Ti's were gone in less than half an hour.
Finally, Linus is far from being a journalist.