NVIDIA has come out to play with three new graphics cards, the GeForce RTX 30 Series. The series forms the second generation of RTX, which introduced real-time ray tracing and includes the RTX 3070, RTX 3080, and RTX 3090. The GeForce RTX 30 series completely overtakes the previous GeForce lineup.
“This is our greatest generational leap ever,” proclaimed NVIDIA CEO Jensen Huang. Huang tends to make strong statements with every release—he first introduced RTX as “the holy grail of computer graphics”—but that doesn’t mean he’s hyperbolizing. Here’s what he means by “greatest generational leap”:
The new GeForce RTX 3070 and 3080 are both more performant than the previous top gun, the GeForce RTX 2080 Ti, and you’ll notice that both are also significantly less expensive. You’ll also observe that the RTX 3090 is missing from the chart. That’s because it’s off it on both axes (more on that in a sec).
The GeForce RTX cards are the first consumer cards to use NVIDIA’s new Ampere architecture, which the company unveiled back in May with the A100 GPU for datacenters. Ampere added an array of improvements, including second-gen RT Cores (for ray tracing), third-gen Tensor Cores (for machine learning), faster GDDR6X graphics memory, and more. The new GeForce GPUs are also manufactured with a custom Samsung 8nm process, rather than the previous generation’s 12nm TSMC process.
Because of all that, NVIDIA is promising that the RTX 30 Series will provide up to 2x the performance and 1.9x the power efficiency of the previous Turing-based cards. Here are the new specs:
Let’s home in on that RTX 3090, a beastly card that Huang referred to as the BFGPU—the Big Ferocious GPU. NVIDIA claims it’s up to 50 percent faster than the Titan RTX, the current king of NVIDIA’s consumer lineup, which it will also replace (the Titan series is no more).
And it is a BFGPU. Just look at Huang holding this thing in his stream introducing the RTX 30 cards:
Here’s where we have to take a step back and recognize that these three new cards, like all GeForce cards, are consumer tier. They’re made for gamers, and gamers are pretty psyched. But NVIDIA also makes a professional lineup of graphics cards, the Quadro series. If you don’t know the differences between the two, read What’s the Difference Between GeForce and Quadro Graphics Cards?
So if these consumer cards are such a generational leap forward, what will the next Quadro cards look like? My hopes are pretty high. That top-of-the-line BFGPU up there boasts 24GB of VRAM, more than double the last-gen 2080 Ti. The current best Quadro card, the Quadro RTX 8000, is already sitting at 48GB. Will we see a new Quadro card with 96GB of VRAM?
Here’s another point of reference. The Quadro RTX 8000 has 4608 CUDA Cores, the main computational element of NVIDIA GPUs. The entry-level GeForce RTX 3070 has 5888, and the BFGPU has a staggering 10,496. How many more cores are we going to see in the next Quadro series?
In the last generation, the Quadro RTX cards were announced before the GeForce RTX card. NVIDIA has switched up that order this generation—perhaps because of an uptick in consumer GPU usage due to stay-at-home gamers. So we’ll have to stay tuned on the Quadro front, but I for one am excited to see what’s coming. So is Huang.
“I can’t wait to go forward 20 years to see what RTX started,” he said. “In this future, GeForce is your holodeck, your lightspeed starship, your time machine. In this future, we will look back and realize that it started here.”
For more NVIDIA news, check out Nvidia Worth More Than Intel as Market Value Exceeds $300 Billion.