Skip to main content

Nvidia may have found a new way to bypass GPU export restrictions

The RTX 4090 graphics card sitting on a table with a dark green background.
Jacob Roach / Digital Trends

Chinese gamers are expected to have limited access to Nvidia’s best graphics card due to strict export restrictions. However, Nvidia may have found a way around it without cutting down its flagship GPU. A new leak suggests that the RTX 5090D will have the same hardware specifications as the worldwide version, and the solution lies in firmware adjustments.

As a quick refresher, the “D” in RTX 5090D stands for “Dragon.” It marks GPUs made by Nvidia to bypass the export restrictions imposed by the U.S. on China, which limit the sale of high-performance graphics processors. We first saw it appear in the RTX 4090D as a remedy for the fact that the base RTX 4090 exceeds the performance thresholds set by these regulations.

Recommended Videos

Initially, Nvidia adopted a simple approach and started selling the RTX 4090D as a cut-down RTX 4090, with fewer CUDA cores and lower power consumption. As VideoCardz notes, they were also not supposed to be overclocked (although people found a way around that in the end). However, it’s easy to imagine that this wouldn’t have worked with the RTX 5090, which is said to be significantly more powerful than its predecessor.

This brings us to today’s leak. As always, remember that we’re dealing with rumors, and the following may not turn out to be true once the RTX 50-series hits the shelves.

The logo for the RTX 5090D.
MEGAsizeGPU

According to Panzerlied, a leaker from the Chiphell forums, the RTX 5090 and the RTX 5090D will be one and the same in terms of specifications. Both will use the GB202 GPU without any hardware adjustments, but Nvidia will limit the AI performance of these GPUs in order to meet the regulations.

It’s unclear what kind of firmware changes Nvidia could add to make sure that the RTX 5090D won’t be quite as useful for AI workloads. One way to go about it would be to limit Tensor core performance, but this would also affect DLSS 3 capabilities. This might make the card much less worth buying for gamers when compared to the RTX 4090D, which, while cut-down, gets the full power of DLSS 3. Nvidia could also slice the card’s default power limit.

This reminds us of the lite hash rate (LHR) limiter versions of RTX 30-series cards. While the GPUs were the same on a hardware level, Nvidia attempted to make them less useful for cryptocurrency miners by including BIOS limiters. Crypto enthusiasts found their way around this pretty quickly, though — whether the same happens to the RTX 5090D remains to be seen.

Monica J. White
Monica is a computing writer at Digital Trends, focusing on PC hardware. Since joining the team in 2021, Monica has written…
Nvidia might once again delay the GPU gamers want most
Two RTX 4060 graphics cards stacked on top of each other.

If a GPU is yet to be announced, can we consider it to be delayed? Maybe, maybe not, but if you trust leakers, Nvidia's upcoming best graphics cards for gamers on a budget are seemingly stuck in limbo. The RTX 5060 and the RTX 5060 Ti are said to be delayed once again, and gamers might have to wait for quite a long time to get their hands on one of the new RTX 50-series GPUs.

This grim update comes from Board Channels, which is a website frequented by people who claim to be affiliated with Nvidia's add-in board (AIB) partners. According to the report, the RTX 5060 Ti (in both its iterations, meaning the 8GB and the 16GB models) will now launch in mid-April, followed by the RTX 5060 in mid-May. Nvidia is said to have notified its AIBs about these delays.

Read more
Nvidia RTX Pro 6000 Blackwell sets a new standard for workstation GPUs
Nvidia RTX Pro 6000 Blackwell GPU

Nvidia announced a host of new GPUs at its GTC 2025 conference on Tuesday, including the RTX Pro Blackwell series. The highlight component of the series is the RTX Pro 6000 Blackwell GPU, developed for workstations. The RTX Pro 6000 Blackwell GPU is also available in variants to support desktops, laptops, and data centers. The component is intended to aid professional designers, developers, data scientists, and creatives, the Verge noted. 

The RTX Pro naming sequence allows the Blackwell-based GPU to stand out against previous architectures, including Ada Lovelace, Ampere, and Turing, as well as the standard consumer product GPUs, Tech Radar Pro noted. 

Read more
Nvidia claims RTX 5000 shipped better than 4000 but gamers are still waiting
The RTX 5090 sitting on a pink background.

Nvidia is trying to make its GeForce RTX 5000 series seem more impressive to the media by suggesting that the latest GPUs are selling better than the previous generation. However, many pundits aren’t buying the claim.

PC Mag pondered whether Nvidia has orchestrated a “paper launch” of the RTX 5000 series, suggesting that there might not be much of a product available for consumers. The majority of the people with their hands on the GPUs, especially the high-end models such as the 5090 and 5080 appear to be reviewers, influencers, and other determined enthusiasts as opposed to everyday gamers, who are still using prior generation GPUs at higher rates.

Read more