The RTX 5090 will reportedly require 600 watts of power

Rumors have been circulating about the RTX 5090 for a while, but we’re finally getting a clearer picture of how Nvidia’s flagship RTX 50-series GPU is shaping up. Well-known hardware leaker Kopite7kimi is claiming the RTX 5090, which seems destined to earn a spot among the best graphics cards, will come with an obscene power requirement of 600 watts.

The leaker shared specs for the RTX 5090 and RTX 5080 on X (formerly Twitter). We’ve seen vague claims from Kopite7kimi in the past concerning RTX 50-series graphics cards, but this is the first time the leaker has shared full specs. According to the leak, the RTX 5090 will require 600W of power and come with a staggering 32GB of GDDR7 memory across a 512-bit bus.

We’ve heard murmurs in the past few months that the RTX 5090 could reach as high as 600W, but this is the first time it’s been brought up alongside other specs. The RTX 4090, by comparison, requires 450W of power. However, the 16-pin power connection the RTX 4090 uses is capable of 600W, and it seems Nvidia could max out that connection with the next-gen RTX 5090. Despite the increased power demands, Kopite7kimi still claims the RTX 5090 will use a dual-slot cooler.

The leaker also shared details about the RTX 5080, claiming the GPU will require 400W and come with 16GB of GDDR7 memory on a 256-bit bus. That’s not a massive improvement in specs compared to the RTX 4080 Super, suggesting Nvidia will keep a large gap in performance between the RTX 5090 and RTX 5080 as it did with its RTX 40-series graphics cards.

Nvidia has yet to confirm that the RTX 5090 and RTX 5080 even exist, though we already know quite a bit about the next-gen Blackwell architecture the GPUs will use. Nvidia has already introduced this architecture to the data center, despite the fact that it was forced to delay the release of its enterprise Blackwell GPUs due to a design flaw.

It’s not clear when Nvidia will introduce its next-gen GPUs to gaming PCs. Following Nvidia’s normal release cadence, we would expect to see the GPUs in October or November — however, given the delay in the enterprise sector, it’s possible the GPUs could get pushed back to 2025.