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

Nvidia’s beastly RTX 4090 moves one step closer to launch

Add as a preferred source on Google

New rumors about Nvidia’s upcoming Ada Lovelace GPU have emerged, revealing that the graphics card may have already entered the testing phase.

The naming of the graphics card, based on the AD102 GPU, is still up in the air — but the same source points to the RTX 40-series being used.

Recommended Videos

Ignore these fanboys, let's turn our attention to GPU.
AD102 has started testing. https://t.co/yziVJE8eFp

— kopite7kimi (@kopite7kimi) April 19, 2022

With the launch of Nvidia’s next series of GPUs set to take place this year, more and more rumors are cropping up as we get closer to the second half of 2022. Today’s news comes from Kopite7kimi, a known leaker on the GPU scene. Much like any leak, this should be taken with a dose of skepticism, but Kopite7kimi has a proven track record, which lends some credibility to these rumors.

The leaker announced that the AD102 GPU has started testing. AD102 is the code name for Nvidia’s next flagship graphics card, pointing toward the top of the upcoming “Ada” line — think the equivalent of the RTX 3090 and RTX 3080, but better. Nvidia hasn’t officially confirmed the naming convention for this series of GPUs yet, but on this, Kopite7kimi also had something to say, stating that “at least [for] now, we can call it RTX 4090.”

If the card has indeed started testing, this spells good news for those who are waiting for its launch. Although no exact release date has been shared yet, speculation points to the second half of the year, more specifically September to November, for the launch. Nvidia may not have started mass-producing the cards yet with a few months left to go, but if this release window remains accurate, it will likely move on to that phase soon.

Assuming that testing samples of the GPU have already been sent out, we can expect to see some early benchmarks popping up soon. However, the GPU is unlikely to shine in such early tests, considering that the drivers have almost certainly not been finalized yet. Even then, there is no doubt that Ada will be a step up for Nvidia.

Kopite7kimi rounded out the leaks by adding that the AD102 GPU will feature 24Gbps memory, although more specifically, the leaker referred to the RTX 4090 in particular. It’s hard to tell whether the RTX 4080 will also feature 24Gbps memory or less. One way or another, with 24Gbps of GDDR6X memory, the Nvidia RTX 4090 will push memory speeds over 1TB/s. Wccftech calculates that this will add up to at least a 15% boost in bandwidth compared to the current tech.

A Nvidia RTX 3090 Ti sits on a silver table.
Nvidia

Nvidia itself hasn’t revealed much about the upcoming flagship, but piecing together various rumors gives us an idea of what it might be like. The AD102 GPU is rumored to have a TDP of up to 600 watts, which means the RTX 4090 is going to be one beefy GPU with high power requirements to match. In order to accommodate this kind of power draw, the cards will have PCIe Gen 5 connectors and will come with a 4 x 8-pin to 1 x 16-pin adapter.

While the rumored RTX 4090 is going to be the flagship, the lineup is, of course, going to feature different variants of the card. We may see designs that go above 20Gbps but have a more modest 8GB and 16GB of memory.

As these cards are going to require a lot of power, thermals might get tricky, so Nvidia is allegedly working with its board partners to introduce quad-slot cooling, and may even use AIO and hybrid cooling options.

The Nvidia RTX 4090 and the rest of the Ada lineup are said to hit the market in the fall. They will undoubtedly feature a performance jump — some sources expect the RTX 4090 to be twice as powerful as the RTX 3090. The pricing and availability are still up in the air. These GPUs could turn out to be very expensive, but then again, we’re all used to that, what with over two years of the GPU shortage.

Monica J. White
Monica is a computing writer at Digital Trends, focusing on PC hardware. Since joining the team in 2021, Monica has written…
Anthropic warns of imminent self-replicating AI that might even work off an oven or TV
Self-replicating AI could be merely months away, and tests show it can run on the devices sitting at your home.
Illustration of dangerous AI.

Over the past few weeks, nearly every AI lab has released frontier AI models. Earlier today, Google started rolling out Gemini 4, Argon, hot on the heels of Meta announcing its Muse Wonder frontier AI models to compete against the best from OpenAI and Anthropic's Claude. This relentless pace of AI model release comes at a time when the same AI labs are calling for development slowdown and increased regulation, following a series of concerning incidents where these AI models went rogue and broke into private, as well as government-owned, websites.

Now, Anthropic has dropped a chilling set of predictions about the capabilities of these AI models after running a series of tests. The company claims that small AI models could be merely a few months away from self-replicating and turning into a dangerous swarm. More importantly, they won't require a massive data center or an uber-powerful computer to do so. On the contrary, the lab claims that these self-replicating AI swarms will need something with as little computing power as an average Internet-connected device, like a smart oven or an Android TV box.

Read more
Gemini 4 Argon is finally available for developers, businesses, and paid users
Google’s most capable Gemini model is now rolling out more widely, but free users are still left out.
Gemini 4 Aragon AI model launched by Google

Google unveiled Gemini 4 Argon at the end of September, and on paper, it looked like the company’s strongest answer yet to the best models from OpenAI and Anthropic. There was just one fairly big problem. Almost nobody could actually use it. At launch, Argon was limited to a small batch of testers, trusted partners, and government work, while Google continued testing the model before a wider release. Two weeks later, Google is finally opening the gates.

Gemini 4 Argon is now available globally to developers and enterprises through the paid Gemini API tier, AI Studio, and Google’s Gemini platform. Google AI Ultra subscribers can also access it through Antigravity, while both Pro and Ultra subscribers can use Argon inside the Gemini app and AI Mode in Search.

Read more
Nvidia’s DLSS 5 is now twice as fast and heading to Hogwarts Legacy
NVIDIA cuts DLSS 5's memory demands while expanding support to more games.
hogwarts-legacy-nvidia-dlss-5-3d-guided-neural-rendering

Nvidia just handed DLSS 5 a major speed upgrade, and the AI graphics tech is finally ready for its proper debut in Hogwarts Legacy. The company's latest model update doubles performance compared to the version that launched DLSS 5 back in March.

What has Nvidia improved in DLSS 5?

Read more