Image: NVIDIA

The boost clocks and maximum TGPs of NVIDIA’s GeForce RTX 4090 and GeForce RTX 4080 graphics cards have seemingly been leaked. “Multiple sources” with VideoCardz can reveal that the flagship GeForce RTX 4090 will offer boost clocks of up to 2,520 MHz and a maximum configurable TGP of 660 watts, while the GeForce RTX 4080 will be offered in two memory configurations, 16 GB and 12 GB, the unique specifications of which can be found in the table below.

Image: VideoCardz

From a VideoCardz report:

[…] there is no RTX 4070 listed for now, and AIBs do not expect this to change (after all, it’s just 6 days until announcement). As far as the launch timeline is concerned, RTX 4090 is expected in the first half of October, while RTX 4080 series should launch in the first two weeks of November. We are waiting for detailed embargo information, so we should have more accurate data soon. To be confirmed are still PCIe Gen compatibility and obviously pricing.

The GeForce RTX 4080 (12 GB) was meant to be the GeForce RTX 4070 or GeForce RTX 4070 Ti until NVIDIA decided to change it at the “last minute,” according to VideoCardz. NVIDIA is expected is announce its first GeForce RTX 40 Series graphics cards and detail the new Ada architecture during next week’s GeForce Beyond event on Tuesday, September 20.

Go to thread

Don’t Miss Out on More FPS Review Content!

Our weekly newsletter includes a recap of our reviews and a run down of the most popular tech news that we published.

6 comments

  1. Nope... nope nope nope. the 4080 12gb is the 4070 clearly otherwise they wouldn't be so different. They needed to keep the 4080 at 16gb but now having a 4080 16gb model and a 1080 12gb with less of everything they can charge whatever they want for the 4080 16gb while keeping the base 4080 matching price to the 3080 at launch while actually being a full model revision lower.

    **** games like this erode consumer sentiment.
  2. I'm wondering what the distinction between default and max are.

    Is the default the stock setting, and max the max allowable overclock?

    Either way, 450W and 660w default and max for the 4090 is pretty beefy.

    I thought my 6900xt with XFX custom power layout which - in my overclock using more power tool - can hit 430w was extreme.
  3. Nope... nope nope nope. the 4080 12gb is the 4070 clearly otherwise they wouldn't be so different. They needed to keep the 4080 at 16gb but now having a 4080 16gb model and a 1080 12gb with less of everything they can charge whatever they want for the 4080 16gb while keeping the base 4080 matching price to the 3080 at launch while actually being a full model revision lower.

    **** games like this erode consumer sentiment.

    Agree.

    The misleading naming in the industry really needs to stop. There is way too much naming two different things the same name explicitly in order to deceive the consumer, and it needs to stop.
  4. Was done before with the 1060 3/6
    It is stupid imo but what would drive Nvidia to do this? Why?


    Pressure from OEM's maybe? So they can print "We include a 4080 in this system!" without indicating which one (at least without reading the detailed specs), and the less informed buyers are never into the details...
  5. I generally only get concerned when they market two different part numbers under the same brand name -

    The 1060 is a good example - where the 3G version was a different chip (GP106, 1152 cores) and the 6G was a faster chip (GP104, 1280 cores)

Leave a comment

Please log in to your forum account to comment