Friday, July 17th 2026
NVIDIA Board Partners Receive RTX 50 SUPER, But GDDR7 Pricing Holds the Release Back
NVIDIA's long-rumored GeForce RTX 50 SUPER graphics cards have been shipped to the company's board partners, but we can't get our hands on them just yet. According to VideoCardz, NVIDIA's board partners have already received the GeForce RTX 50 SUPER silicon, but the release is on hold by Team Green headquarters. This means that while the GPUs are physically with the board partners, they can't proceed with the launch due to a shortage of GDDR7 memory chips. It was previously rumored that the "SUPER" series was planned to feature denser GDDR7 memory modules, offering 3 GB of capacity per chip, which would increase the memory configuration of the standard GeForce RTX 5070, RTX 5070 Ti, and RTX 5080. Initially, the RTX 5070 SUPER was expected to be upgraded to offer 18 GB, while the RTX 5070 Ti SUPER and RTX 5080 SUPER would each provide 24 GB of GDDR7 memory.
Meanwhile, all other specifications will remain the same. However, since the 3 GB GDDR7 memory modules are being used in other products like NVIDIA's AI GPU portfolio, including the RTX PRO 6000 "Blackwell" and "Rubin CPX," the company has likely decided to prioritize this high-margin business. The availability of 3 GB GDDR7 modules is much lower than the current industry demand. As a result, gamers are left with the regular GeForce RTX 50 series for now, which uses the more readily available 2 GB GDDR7 memory modules.
Additionally, gamers have noticed that the online Seasonic PSU calculator has reignited rumors about the RTX 50 SUPER refresh. According to information in the PSU calculator, the RTX 5080 SUPER is rated at a TGP of 415 W, which is a 55 W increase over the RTX 5080's 360 W, as reported by the same Seasonic PSU calculator. Similarly, the RTX 5070 Ti SUPER will see a 50 W increase over the 5070 Ti's 300 W, for a TGP of 350 W, while the RTX 5070 SUPER is rated at 275 W, compared to the 250 W of the original RTX 5070. These increases are due to the enhanced memory capacity, which likely draws more power to run these 3 GB modules smoothly. With no additional CUDA cores, the RTX 50 SUPER refresh could also offer slight frequency improvements to justify the higher TGP ratings.
Source:
VideoCardz
Meanwhile, all other specifications will remain the same. However, since the 3 GB GDDR7 memory modules are being used in other products like NVIDIA's AI GPU portfolio, including the RTX PRO 6000 "Blackwell" and "Rubin CPX," the company has likely decided to prioritize this high-margin business. The availability of 3 GB GDDR7 modules is much lower than the current industry demand. As a result, gamers are left with the regular GeForce RTX 50 series for now, which uses the more readily available 2 GB GDDR7 memory modules.
47 Comments on NVIDIA Board Partners Receive RTX 50 SUPER, But GDDR7 Pricing Holds the Release Back
board partners: "oh, so there's a memory shortage? Who's consuming them?"
Nvidia: "oh...well...we have all the memory, we're just not giving you any for consumer products...we don't want their money because there's more money to be made from the companies we've invested money in to make sure they agree to buy our products at inflated rates, thus boosting both of our stock prices"
Consumers: "wtf..."
However, for most games that are 1080, then there really isn't a need to go above 8GB VRAM, 2k res, 8GB is kinda low, need more like 10-12GB and 4K you need 16GB cards at minimum
Either way, if the 5070 Super did launch right now, it'd probably be the same price as a 5070Ti which blows it out of the water.
Nvidia want you to buy an RTX Pro 2000 Blackwell for 16GB models, for twice the price.
CUDA is the only API that matters, and many of the tools don't care if it's a Geforce or an RTX Pro.
Why would board partners buy the main chip, if they dont already have the RAM coming in?
Having expensive chips sitting in storage for an unkown timeline seems really risky. And especially in IT where things tend to drop in value quite fast due to the constant tick/tock development.
And why would they be buying from nVidia at all, knowing that the one component they cant get is being held back by nVidia themselves?
www.tomshardware.com/pc-components/gpus/nvidia-reportedly-no-longer-supplying-vram-to-its-gpu-board-partners-in-response-to-memory-crunch-rumor-claims-vendors-will-only-get-the-die-forced-to-source-memory-on-their-own
Is nV still bundling GPU dies and VRAM or are board partners now sourcing memory themselves (or jointly)? It wasn’t long ago reports suggested Nvidia might stop supplying memory as part of the package. If thats in effect, these board partners could be in some seriously rough waters unless their contracts allow for full cancellations/returns without the naughty tax.