The design of the new generation NVIDIA GeForce RTX 40 series Founders Edition is allegedly leaked. QbitLeaks. The new design gives us a look at the updated Founders Edition GPU cooler that will be featured on high-end Ada Lovelace GPUs like the RTX 4090 and 4080.
NVIDIA’s Massive GeForce RTX 40 Founders Edition Cooler Allegedly Leaked, Coming Soon to RTX 4090 and RTX 4080 Graphics Cards!
According to the leak, this new cooler design pictured will be part of the GTC ’22 keynote in two weeks. There are no details on what card this is, but the updated shroud and fan design seem to match it Leaked RTX 4080 cooler a few days ago. It looks like NVIDIA will reuse the existing cooler design and give it a minor visual overhaul.
we saw in it previous leaks shows that the under-the-hood cooler has been updated with a larger thermal contact surface area covering the GPU, VRAM, and VRMs. The fans have been updated to a 7-blade fan design and are slightly larger, but the overall appearance of the casing and design remains largely the same as the current Founders Edition graphics cards. This updated design should help provide better cooling for the Ada Lovelace GPUs, which will consume a lot of power. The cards will also use a PCIe Gen 5.0 connector interface and a Gen 5.0 power interface via new 16-pin connectors.
NVIDIA GeForce RTX 4090 Founders Edition Graphics Card Cooler / Shroud Leak:
NVIDIA GeForce RTX 4080 Founders Edition Graphics Card Cooler / Shroud Leak:

The leaker states that this image is a teaser for GTC, so we can definitely see CEO Jensen talking about the next-gen gaming lineup during the event. GTC used to be a data center and HPC-specific event, but with NVIDIA’s recent decline in profits, mainly due to the slumping gaming market, the company has redefined its main event and dedicated it to gamers.
NVIDIA GeForce RTX 4080 ‘Expected’ Specifications
NVIDIA GeForce RTX 4080 While the previous configuration offered 80 SM or 10,240 cores, it is expected to use the AD103-300 GPU configuration with 9,728 cores or 76 SM enabled out of a total of 84 units. While the full GPU packs 64MB of L2 cache and 224 ROPs, the RTX 4080 can end up with a lower ROP thanks to its 48MB L2 cache and reduced design. The card is expected to be based on the PG136/139-SKU360 PCB.

As for memory specs, the GeForce RTX 4080 is expected to rock 16GB of GDDR6X capacities, said to be clocked at 23Gbps on a 256-bit bus interface. This will provide a throughput of up to 736 GB/s. This is still slightly slower than the 760GB/s throughput offered by the RTX 3080, as it comes with a 320-bit interface but less than 10GB of capacity. To compensate for the low bandwidth, NVIDIA may incorporate a next-generation memory compression suite to compensate for the 256-bit interface.
For power, the TBP is now rated at 340W, a 20W increase from the 320W spec we got. This puts the TBP on the same playing field as the current RTX 3080 graphics card (up to 350W). Now, it’s not known if other RTX 40-series graphics cards will get the faster GDDR6X memory treatment, but we do know that Micron has. started Full mass production of GDDR6X memory modules up to 24 Gbps, so they have to go somewhere.
- NVIDIA GeForce RTX 4080 “Expected” TBP – 340W
- NVIDIA GeForce RTX 3080 “Official” TBP – 350W
NVIDIA GeForce RTX 4080 Series Initial Specifications:
The name of the graphics card | NVIDIA GeForce RTX 4080 Ti | NVIDIA GeForce RTX 4080 | NVIDIA GeForce RTX 3090 Ti | NVIDIA GeForce RTX 3080 |
---|---|---|---|---|
GPU name | Ada Lovelace AD102-250? | Ada Lovelace AD103-300? | Ampere GA102-225 | Ampere GA102-200 |
Process node | TSMC 4N | TSMC 4N | Samsung 8nm | Samsung 8nm |
Die size | ~450mm2 | ~450mm2 | 628.4 mm2 | 628.4 mm2 |
transistors | TBD | TBD | 28 billion | 28 billion |
CUDA cores | 14848 | 9728? | 10240 | 8704 |
TMU / ROP | TBD / 232? | TBD / 214? | 320 / 112 | 272 / 96 |
Tensor / RT kernels | TBD / TBD | TBD / TBD | 320/80 | 272 / 68 |
Main clock | TBD | TBD | 1365 MHz | 1440 MHz |
Power up the clock | ~2600 MHz | ~2500 MHz | 1665 MHz | 1710 MHz |
FP32 Calculation | ~55TFLOPs | ~50 TFLOPS | 34 TFLOP | 30 TFLOP |
RT TFLOPs | TBD | TBD | 67 TFLOP | 58 TFLOP |
Tensor-TOPS | TBD | TBD | 273 TOP | 238 TOP |
Memory Capacity | 20 GB GDDR6X | 16GB GDDR6X? 12 GB GDDR6X? |
12 GB GDDR6X | 10 GB GDDR6X |
Memory bus | 320-bit | 256-bit? 192-bit? |
384-bit | 320-bit |
Memory speed | 21.0 Gbps? | 23.0 Gbps? | 19 Gbps | 19 Gbit/s |
Tape | 840 GB/s | 736 GB/s? 552 GB/s? |
912 Gbps | 760 Gbit/s |
TBP | 450W | 340W | 350W | 320W |
Price (MSRP/FE) | $1199 US? | 699 USD? | 1199 dollars | 699 USD |
Start (Availability) | 2023? | July 2022? | June 3, 2021 | September 17, 2020 |
NVIDIA GeForce RTX 4090 ‘Expected’ Specifications
The NVIDIA GeForce RTX 4090 will use 128 SMs from 144 SMs for a total of 16,384 CUDA cores. The GPU will be packed with 96MB of L2 cache and a total of 384 ROPs, which is simply insane. Clock speeds have yet to be confirmed, but given that the TSMC 4N process is used, we expect clocks in the 2.0-3.0 GHz range.
As for memory specs, the GeForce RTX 4090 is expected to rock 24GB of GDDR6X capacities running at 21Gbps on a 384-bit bus interface. This will provide bandwidth up to 1 TB/s. That’s the same bandwidth as the current RTX 3090 Ti graphics card, and when it comes to power consumption, the TBP is said to be rated at 450W, which suggests the TGP could be lower than that. The card will be equipped with a single 16-pin connector that provides up to 600W of power. It’s likely we’ll get 500W+ custom designs like we saw with the RTX 3090 Ti.

When it comes to feature set, NVIDIA GeForce RTX 4090 and RTX 4080 graphics cards will rock all modern NV feature sets like latest 4th Gen Tensor cores, 3rd gen RT cores, latest NVENC Encoder and NVCDEC Decoder. latest APIs. They will also pack all modern RTX features such as DLSS, Reflex, Broadcast, Resizable-BAR, Freestyle, Ansel, Highlights, Shadowplay and G-SYNC support.
- NVIDIA GeForce RTX 4090 “Expected” TBP – 450W
- NVIDIA GeForce RTX 3090 “Official” TBP – 350W
NVIDIA GeForce RTX 4090 Ti & RTX 4090 “Initial” Specifications:
The name of the graphics card | NVIDIA GeForce RTX 4090 Ti | NVIDIA GeForce RTX 4090 | NVIDIA GeForce RTX 3090 Ti | NVIDIA GeForce RTX 3090 |
---|---|---|---|---|
GPU name | Ada Lovelace AD102-350? | Ada Lovelace AD102-300? | Ampere GA102-350 | Ampere GA102-300 |
Process node | TSMC 4N | TSMC 4N | Samsung 8nm | Samsung 8nm |
Die size | ~600mm2 | ~600mm2 | 628.4 mm2 | 628.4 mm2 |
transistors | TBD | TBD | 28 billion | 28 billion |
CUDA cores | 18432 | 16128 | 10752 | 10496 |
TMU / ROP | TBD / 384 | TBD / 384 | 336 / 112 | 328 / 112 |
Tensor / RT kernels | TBD / TBD | TBD / TBD | 336 / 84 | 328 / 82 |
Main clock | TBD | TBD | 1560 MHz | 1400 MHz |
Power up the clock | ~2800 MHz | ~2600 MHz | 1860 MHz | 1700 MHz |
FP32 Calculation | ~103 TFLOPS | ~90 TFLOPS | 40 TFLOP | 36 TFLOP |
RT TFLOPs | TBD | TBD | 74 TFLOP | 69 TFLOP |
Tensor-TOPS | TBD | TBD | 320 TOP | 285 TOP |
Memory Capacity | 24 GB GDDR6X | 24 GB GDDR6X | 24 GB GDDR6X | 24 GB GDDR6X |
Memory bus | 384-bit | 384-bit | 384-bit | 384-bit |
Memory speed | 24.0 Gbps | 21.0 Gbps | 21.0 Gbps | 19.5 Gbps |
Tape | 1152 GB/s | 1008 GB/s | 1008 GB/s | 936 Gbps |
TGP | 600W | 450W | 450W | 350W |
Price (MSRP/FE) | 1999 USD? | $1499 US? | 1999 USD | 1499 USD |
Start (Availability) | 2023? | October 2022? | March 29, 2022 | September 24, 2020 |
NVIDIA GeForce RTX 40 series graphics cards, including the RTX 4080 and RTX 4070 graphics cards, will be among the first graphics cards to be introduced to gamers alongside the RTX 4090. The RTX 4090 is expected to launch on October 22 so far, but the launch will Expected at NVIDIA’s GTC launch later this month.
Products mentioned in this article