Rumored Nvidia GeForce RTX 40-Series Specs Leak on Twitter

Nvidia GeForce RTX 3080 Founders Edition
(Image credit: Nvidia)

Kopite7kimi, a well-known leaker on Twitter, has published what may be the first specifications of Nvidia's upcoming GeForce RTX 40-series graphics cards family. Since we are several months away from Nvidia's launch of its codenamed Ada Lovelace architecture, it's possible there will be changes, but given the leaker's track record, the specs are at least worth considering. 

Nvidia's initial GeForce RTX 40-series family will consist of three graphics cards: the GeForce RTX 4090, based on the AD102-300 graphics processor paired with 24GB of GDDR6X memory; the GeForce RTX 4080, powered by the AD103-300 GPU mated with 16GB of GDDR6/GDDR6X memory; and the GeForce RTX 4070 featuring the AD104-275 chip equipped with 10GB of GDDR6. 

The number of CUDA cores featured by Nvidia's Ada Lovelace GPUs show that the new graphics boards will likely have a considerable performance increase when compared to Nvidia's existing GeForce RTX 30-series, which are among best graphics cards around

Rumored Nvidia GeForce RTX 40-Series Specifications

Swipe to scroll horizontally
Row 0 - Cell 0 GPUFP32 CUDA CoresMemory ConfigurationTBP
GeForce RTX 4090AD102-3001638424GB 384-bit 21GT/s GDDR6X450W
GeForce RTX 4080AD103-3001024016GB 256-bit 18GT/s GDDR6?420W
GeForce RTX 4070AD104-275716810GB 160-bit 18GT/s GDDR5300W

All these initial GeForce RTX 40-series graphics boards will allegedly be quite power hungry with the top-of-the-range product featuring a thermal board power (TBP) of 450W and other rated for 420W and 300W, respectively. When it comes to power consumption, the information corroborates with earlier rumors indicating a major increase of TBP for Ada Lovelace family

While power consumption of Nvidia's next-generation GeForce RTX 40-series products will increase compared to current-generation graphics cards, not everything is clear about pricing of the new boards. Kopite7kimi tells us not to expect GeForce RTX 4000 boards to feature lower MSRPs. Price is a particularly murky topic, keeping in mind higher production costs on TSMC's N5 process technology (or rather customized 4N) when compared to Samsung's 8LPP. 

It is noteworthy that this time around Nvidia will use three different graphics processors for three initial cards. This might be a result of decent initial yields of Nvidia's Ada Lovelace GPUs at TSMC, or perhaps due to some changes in the company's internal chip design schedules. Anyhow, the gaps between the number of CUDA cores featured by the AD102, AD103 and AD104 GPUs might indicate that Nvidia will be very flexible with configurations for refresh (Ti-branded or Super-branded products). 

Of course, Nvidia typically does not comment on specifications of unreleased products, so take the information with a grain of salt.

Anton Shilov
Contributing Writer

Anton Shilov is a contributing writer at Tom’s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends.

  • warezme
    The 4090 will be my next new beast and finally retire my trusty but aging 2080ti. I decided to skip the entire 3000 series.
  • AgentBirdnest
    60% more cores and faster memory on the 4090 compared to 4080, with only a 7% (30W) higher TBP? And it doesn't gain one watt over the 3090 Ti, while the 4080 is 100W more than the 3080? What demonry is this?
    All the rumors just haven't been adding up, to me...
    What's with the huge gap between "4080" and "4090", core-wise?
    And has it been addressed why AD103 is assumed to be desktop, when the "03" has been reserved for mobile since at least the 900-series?
    Seems much more likely to me that the AD102 would be both the 4090 and 4080, at 450W and 420W respectively. AD103 would be a mobile chip. AD104 would be a 4070.
    /my thoughts.

    Doesn't Nvidia usually chooses prices much closer to release (as in: day of the announcement) ?
    Sorry for so many question marks in this post. :LOL:
  • munkee_zero
    With the 4090 and 4080 both running at over 400W, I think they are going to be a bit toasty. 🔥

    You'll need at least a 1000W upwards PSU from the get go.

    Update: I saw this on Gamers Nexus' YouTube channel. In relation to the increased power demand these new cards will have. (Video link should work in forum view.)

  • Fs19Man68000
    I think it’s neat how much technology has grown in the past few years. The 4090 has 24gb of video ram, my old but reliable Gigabyte GT 1030 has 2gb.
  • Eximo
    AgentBirdnest said:
    What's with the huge gap between "4080" and "4090", core-wise?

    And has it been addressed why AD103 is assumed to be desktop, when the "03" has been reserved for mobile since at least the 900-series

    Doesn't Nvidia usually chooses prices much closer to release (as in: day of the announcement) ?

    Room for 4080 Ti, 4080 Super, etc, which will be an in between card of some sort. Likely less memory and a slightly crippled version of the 4090 GPU. As usual Nvidia will see what the competition is up to and if there is a price point they can match, they will make a SKU that fits in logically.

    There is no 103 chip that I can find, 100, 102, 104, and 106 and 107 in recent times. In the past 119, 117 were also common numbers.

    If they really are doing a completely separate 103 chip, that would also explain the gap, it would be a smaller chip with the 4080 at the top. Not sure why the 4070 would then drop a further chip and not just be a 103-275 vs a 103-300. It could be they plan to have some overlap and use chips from multiple lines to make particular models. Wouldn't be the first time.

    Pricing has to be done a little in advance so that they can pay import duties and the like.
  • osfanbuff63
    I can't see the 4070 being GDDR5, given both AMD and Nvidia don't have GDDR5 models in RDNA 2/Ampere (respectively), and I don't think that Nvidia does in 20-series at all either. The most recent Nvidia card using GDDR5 was the 1650 I think.
  • Geezer760
    And in a year and a half after the 40 series is out, Here come the 50 series, and the sh#t starts all over again, while they laugh all the way to the bank. I don't get the point of spending $800 - $1500 on a gpu just to play a $60 game.
  • Phaaze88
    Aww yeah - just know that there will be Tis/Supers in between those depending on how/what AMD does. Might as well just wait for those or the Radeon 7x50 models...
  • Alvar "Miles" Udell
    Yeah...I wouldn't touch a card with a 400w or higher TBP that's not hybrid liquid cooled, even if it has a 3 or 4 slot air cooler. I don't use headphones and I value my hearing.
  • hannibal
    when prices of nvidia gpus still are far above msrp, it is easy to see that msrp does not come down for the next gen...