Skip to main content
  1. Home
  2. Computing
  3. Trash
  4. News

Upcoming Nvidia GPUs may require monstrous levels of power

Add as a preferred source on Google

The ongoing speculation that Nvidia’s next-gen GeForce RTX 4090 will have monstrous power requirements continues to be confirmed by more and more sources.

YouTuber Moore’s Law is Dead talked about the power draw of the RTX 4090 in his latest video, speculating that the GPU will have a total board power (TBP) of 600 watts, and that figure will only increase with nonreference designs.

RTX 4090 600w TBP Leak: Lovelace is CONFIRMED to be INSANE! (+ RX 6x50 XT Update)

Nvidia’s upcoming Ada Lovelace graphics cards have long been rumored to need intense amounts of power in order to run. Moore’s Law is Dead talked about both the consumer flagship AD102 GPU and the workstation RTX L6000, and everything points to all the talk being true — both these GPUs will need beastly PSUs.

Some reports about the AD102 GPU estimated the power draw at a massive 850-watt TBP. However, these numbers will hopefully go down, and the flagship is often rumored to have a TBP of 600 watts. However, this applies to the base configuration released by Nvidia.

Most commonly, Nvidia’s partners release even more powerful versions of the GPU, so it’s very likely that we will see even higher requirements in those nonreference designs. As an example, the reference model for the RTX 3090 Ti has a 450-watt TBP, but custom models go up to 516 watts. The same is going to be true for the next generation of cards, so even if the Nvidia model manages to squeeze the TBP down to 600 watts (which is still a lot), the custom models may bring it right back up.

Unsurprisingly, such a large power draw will require lots of cooling. Although Nvidia itself may stick to just fans, with perhaps a quad-fan design, the rumor mill points to its board partners switching to hybrid cooling with some AIO cooling added into the mix.

Wccftech speculates about the difference in power requirements for the RTX 4080 versus the flagship RTX 4090. Assuming that the reference model of the RTX 4090 has a 600-watt TBP, it’s likely that we may see up to 450 watts (or more) for the RTX 4080.

Fans on the Nvidia RTX 3080.
Jacob Roach / Digital Trends

Having such a beastly graphics card, most commonly paired with one of the best CPUs, will result in unprecedented needs when it comes to picking the right power supply for your rig. Previously, leakers like harukaze5719 on Twitter already speculated that the GPU would require at least a 1000-watt gold power supply, but that was in reference to the RTX 4090 Ti. However, as Wccftech points out, a 1000- or even 1200-watt PSU may become the new standard as we settle into the next generation of computer hardware.

Nvidia’s upcoming workstation lineup is also getting updated to the AD102 GPU. The best variant of the card, dubbed either the RTX L6000 or RTX L8000, is expected to have a TBP of at least 320 watts, but that number could go up to as high as 375 watts. Compared to the estimations for the RTX 4090, that seems perfectly reasonable, but it still marks a 25% increase in power draw from the previous generation.

There is no doubt that Nvidia’s next-gen top card is going to require a lot of power. While the exact figures will remain a topic of speculation until Nvidia officially announces the GPUs, mentally preparing yourself to buy a new power supply seems like a wise thing to do if you’re looking to upgrade your GPU this year.

Monica J. White
Monica is a computing writer at Digital Trends, focusing on PC hardware. Since joining the team in 2021, Monica has written…
Substack now lets you check if a post was written by AI
A new Pangram-powered scanner lets you check posts, notes, and replies for signs of AI writing.
Video playing on Substack.

Substack is giving readers a way to check whether the post they're reading was written by a human or by a chatbot. The company has partnered with AI-detection firm Pangram to introduce new tools that will let users scan posts, notes, and replies for AI-generated text. CEO Chris Best introduced the features in a post titled "Against Claudefishing," his term for content that leans on AI while presenting itself as human work.

How the scanning tool works

Read more
China’s AI talent shortage has tech giants recruiting teenagers
Forget campus recruiting, china's biggest tech firms are betting on teenage coders.
Artificial Intelligence

A 13-year-old boy in Hangzhou has already won national AI competitions and built a following of more than 136,000 people online, all while his dad tries to figure out how to guide him through a field that barely existed when he himself was growing up. That family's situation, first reported by Rest of World, says a lot about where China's tech industry is heading right now.

Companies used to wait for graduates to walk through the door. Now they're reaching further back, first to undergrads, and increasingly to teenagers, hoping to spot rare talent before anyone else gets to them.

Read more
OpenAI says AI models autonomously pulled off a major hack, but only a Chinese AI helped recovery
OpenAI

OpenAI’s latest cybersecurity test produced a result that sounds like a cautionary sci-fi script. Its AI models managed to escape their sandbox and reached the open internet. This is where things took a scary turn as it began hacking Hugging Face to steal the answers to the test they were taking.

The company says GPT-5.6 Sol and a more capable unreleased model autonomously chained together vulnerabilities across OpenAI’s research systems and Hugging Face’s production infrastructure. OpenAI has described the event as an unprecedented cyber incident.

Read more