Compared to the previously released GeForce RTX 2080, the new SUPER GPU is equipped with additional CUDA, RT and Tensor Cores, as well as 15.5 Gbps GDDR6 VRAM that increases memory bandwidth to 496.1 GB/s (a 10.7% improvement).
NVIDIA® GeForce RTX™ 40 Series GPUs are beyond fast for gamers and creators. They’re powered by the ultra-efficient NVIDIA Ada Lovelace architecture which delivers a quantum leap in both performance and AI-powered graphics.
Experience lifelike virtual worlds with ray tracing and ultra-high FPS gaming with the lowest latency. Discover revolutionary new ways to create and unprecedented workflow acceleration. The Ada architecture unleashes the full glory of ray tracing, which simulates how light behaves in the real world.
With the power of RTX 40 Series and third-gen RT Cores, you can experience incredibly detailed virtual worlds like never before. Since it was reported that Nvidia would be holding off until 2025 to release the RTX 50-series, questions have swirled about a potential mid-cycle refresh.
The company left a few sizable gaps in its Ada Lovelace lineup in anticipation of such an event, and now it appears it’s planning several “Super” cards to both plug those holes and hit back at AMD.
Box art for the upgraded GPUs seems to confirm their existence, with one source saying Nvidia plans to unveil them at CES in January 2024.
Though we always need to wait for Nvidia to announce something officially, the rumors indicate Nvidia will offer Super variants of three GPUs: the RTX 4080, 4070 Ti, and 4070.
The company can’t seem to decide whether it wants to go with Super or Ti as the branding for an upgraded variant of a particular card, as it used Super for Turing and Ti for Ampere.
With Ada Lovelace, it’s apparently using both, as box art has appeared for the 4070 Ti Super, which is a bit over the top, but that particular GPU has always been a strange duck.
It was first branded as an RTX 4080, as you might recall, before being relegated to 4070 Ti status. We’ve covered the possible updates to these GPUs, with the changes ranging from mild to not terrible, depending on the card.
It’s unlikely any of them will offer a substantial boost over the existing card, which is probably why Nvidia is going with Super instead of Ti this time since Ti cards are typically in a different strata than their siblings.
If you recall, the Super cards from the Turing era offered very mild upgrades, but with the caveat that they were sold for the same price as their predecessors or lower, making them a decent value.
However, now two notable leakers of pre-release info have dug up some new information about the cards. Those leaks show the cards are tipped for a launch at CES, according to kopite7kimi on X.
This makes sense since Nvidia always wants to be present at the show. We also have what appears to be box art for at least one of the GPUs via Mega Size GPU, showing Nvidia has switched from lime green branding to silver to offer a contrast.
As always, the sticking point for most people will be pricing, which is still TBD. Nvidia has caught a ton of flack with the pricing for its 40-series cards, so the Super redo is a chance for it to make things right. Whether it makes these cards sanely priced is a big question.
It could always stick to its guns because it’s making enough money on its data center GPUs to make GeForce sales a secondary consideration on its balance sheet.
However, it does want to pummel AMD every chance it gets, and the company’s RX 7900, 7800, and 7700 XT cards are encroaching on its turf, so it’s possible they’ll be priced to hurt AMD as much as possible.
Max Quality. Powered by AI.
DLSS is a revolutionary breakthrough in AI graphics that multiplies performance. Powered by the new fourth-gen Tensor Cores and Optical Flow Accelerator on GeForce RTX 40 Series GPUs, DLSS 3 uses AI to create additional frames and improve image quality.
See How DLSS Works
Boosts performance by using AI to generate more frames while maintaining great responsiveness with NVIDIA Reflex. DLSS analyzes sequential frames and motion data from the new Optical Flow Accelerator in GeForce RTX 40 Series GPUs to create additional high quality frames.
DLSS Ray Reconstruction
Enhances image quality for all GeForce RTX GPUs by using AI to generate additional pixels for intensive ray-traced scenes. DLSS replaces hand-tuned denoisers with an NVIDIA supercomputer-trained AI network that generates higher-quality pixels in between sampled rays.
DLSS Super Resolution
Boosts performance for all GeForce RTX GPUs by using AI to output higher resolution frames from a lower resolution input. DLSS samples multiple lower resolution images and uses motion data and feedback from prior frames to reconstruct native quality images.
NVIDIA Reflex
Victory Measured in Milliseconds. NVIDIA Reflex and GeForce RTX 40 Series GPUs deliver the lowest latency (ms) and best responsiveness for the ultimate competitive advantage. Built to optimize and measure system latency, Reflex provides faster target acquisition, quicker reaction times, and the best aim precision for competitive games.
Wrapping Up
Discover the RTX AI advantage. Built for the era of AI, GeForce RTX™ GPUs feature specialized AI Tensor Cores that deliver cutting-edge performance and revolutionary capabilities.
From enhanced creativity and ultra-efficient productivity to blisteringly fast gaming, the ultimate in AI power on Windows PCs is on RTX.
Take your creative projects to the next level with NVIDIA Studio. Powered by new dedicated hardware, RTX 40 Series unlocks unmatched performance in 3D rendering, video editing, and graphic design.
Experience feature-rich RTX accelerations in top creative apps, world-class NVIDIA Studio drivers engineered to provide maximum stability, and a suite of exclusive tools that harness the power of RTX for AI-assisted creative workflows.
Who needs a powerful GPU?
GPUs can be used for video editing, 3D graphics rendering, and much more. With a high processing throughput, GPUs can process more data than their Central Processing Unit (CPU) counterparts, making them uniquely suited for highly demanding tasks such as machine learning and cryptocurrency mining.