yitit
Home
/
Hardware
/
NVIDIA GeForce RTX 4080 16 GB & RTX 4080 12 GB Rumored To Launch At The Same Time
NVIDIA GeForce RTX 4080 16 GB & RTX 4080 12 GB Rumored To Launch At The Same Time-February 2024
Feb 12, 2026 9:22 PM

NVIDIA is now rumored to launch not one but two variants of its GeForce RTX 4080 graphics card with 16 GB & 12 GB memory capacities. The latest rumor comes from MEGAsizeGPU who stated the two graphics cards in his previous leak and it looks like Kopite7kimi does seem to believe that NVIDIA launching two RTX 4080 variants might be possible.

NVIDIA Rumored To Launch GeForce RTX 4080 In 16 GB & 12 GB Flavors At The Same Time

Following yesterday's rumor, it was stated that NVIDIA was working on two NVIDIA GeForce RTX 4080 graphics cards. One variant was to feature 16 GB GDDR6X VRAM & a 12-layer PCB while the other variant was said to feature a 12 GB GDDR6X VRAM configuration and a 10-layer PCB design. The first card will be aimed primarily at an AIC and Reference design while the second model will only be an AIC variant.

4080 16G and 4080 12G will be released and launched at the same time, just like 1060 6G and 1060 3G https://t.co/nTWYuSGZUm

— MEGAsizeGPU (@Zed__Wang) September 6, 2022

The NVIDIA GeForce RTX 4080 12 GB is also rumored to utilize a PCB different than the RTX 4080 16 GB variant. Now if we compare this to NVIDIA's GeForce RTX 3080 lineup, we will see that the green team also had two variants of their previous card, one with a 10 GB configuration which launched in 2020, and the other with 12 GB memory and that launched in 2022. The second variant was only limited to AIC models and never saw a Founders Edition launch. AICs also dictated the prices of the card as NVIDIA had no official MSRP mentioned at launch. But the memory configuration wasn't the only thing that changed between the two cards.

The RTX 3080 10 GB & 16 GB featured different core configurations too with the 12 GB variant adding more cores, more VRAM, and a bigger bus interface. The same is expected as the case for the RTX 4080 series. But instead of waiting for a year or more to get the 16 GB variant, it looks like both the 12 GB & 16 GB flavors would be available at launch. The RTX 4080 is indeed real and was leaked out just a few days ago with its updated and thicker shroud design.

There was a plan to make RTX 4090 with AD103, but now it may be RTX 4080 16G. https://t.co/VyErL2swP2

— kopite7kimi (@kopite7kimi) September 5, 2022

Some updates.

We already know some specs, but the corresponding relationship between specs and models has not been determined.

There is a possibility,

PG141-SKU340/341=RTX 4080 12G;

PG141-SKU336/337=RTX 4070.

— kopite7kimi (@kopite7kimi) September 5, 2022

Kopite7kimi believes that the RTX 4080 12 GB will be getting the PG141-SKU340/341 PCB which will suggest that the card might end up with the AD104 GPU core but it doesn't make sense since their will be a huge core configuration difference between the 12 GB and 16 GB model if that was going to happen. What's more likely is that the AD104 and AD103 GPUs could be pin-compatible on the same PCB and both the 12 GB and 16 GB models might end up using the AD103 die with the 12 GB variant being slightly cut-down to a 192-bit bus and lower cores.

NVIDIA GeForce RTX 4080 'Expected' Specifications

The NVIDIA GeForce RTX 4080 is expected to utilize a cut-down AD103-300 GPU configuration with 9,728 cores or 76 SMs enabled of the total 84 units whereas the previous configuration offered 80 SMs or 10,240 cores. While the full GPU comes packed with 64 MB of L2 cache and up to 224 ROPs, the RTX 4080 might end up with 48 MB of L2 cache and lower ROPs too due to its cut-down design. The card is expected to be based on the PG136/139-SKU360 PCB.

NVIDIA GeForce RTX 4080 Reportedly Features 16 GB & 12 GB Flavors, RTX 4090 PCB Details Leaked 2

As for memory specs, the GeForce RTX 4080 is expected to rock 16 GB GDDR6X capacities that are said to be adjusted at 23 Gbps speeds across a 256-bit bus interface. This will provide up to 736 GB/s of bandwidth. This is still a tad bit slower than the 760 GB/s bandwidth offered by the RTX 3080 since it comes with a 320-bit interface but a lowly 10 GB capacity. To compensate for the lower bandwidth, NVIDIA could be integrating a next-gen memory compression suite to make up for the 256-bit interface.

For power, the TBP is now set to be rated at 340W, a 20W increase from the previous 320W spec that we got. This brings the TBP to the same ballpark as the existing RTX 3080 graphics card (up to 350W). Now it is not known whether the other RTX 40 series graphics cards will also be getting the faster GDDR6X memory treatment but we know that Micron has commenced full mass production of up to 24 Gbps GDDR6X memory modules so they have to go somewhere.

NVIDIA GeForce RTX 4080 "Expected" TBP - 340WNVIDIA GeForce RTX 3080 "Official" TBP - 350W

The NVIDIA GeForce RTX 4080 and RTX 4070 graphics cards will be amongst the first graphics cards besides the RTX 4090 to launch to gamers. The RTX 4090 is so far expected to launch on October 22 but an unveiling is expected at NVIDIA's GTC keynote later this month.

NVIDIA GeForce RTX 40 Series Official Specs:

Graphics Card NameNVIDIA GeForce RTX 4090NVIDIA GeForce RTX 4090 DNVIDIA GeForce RTX 4080NVIDIA GeForce RTX 4070 TiNVIDIA GeForce RTX 4070NVIDIA GeForce RTX 4060 TiNVIDIA GeForce RTX 4060
GPU NameAda Lovelace AD102-300Ada Lovelace AD102-250Ada Lovelace AD103-300Ada Lovelace AD104-400Ada Lovelace AD104-250Ada Lovelace AD106-350Ada Lovelace AD107-400
Process NodeTSMC 4NTSMC 4NTSMC 4NTSMC 4NTSMC 4NTSMC 4NTSMC 4N
Die Size608mm2608mm2378.6mm2294.5mm2294.5mm2190.0mm2146.0mm2
Transistors76 Billion76 Billion45.9 Billion35.8 Billion35.8 Billion22.9 BillionTBD
CUDA Cores16384TBD97287680588843523072
TMUs / ROPs512 / 176TBD320 / 112240 / 80184 / 64136 / 48TBD
Tensor / RT Cores512 / 128TBD304 / 76240 / 60184 / 46136 / 34TBD
L2 Cache72 MBTBD64 MB48 MB36 MB32 MB24 MB
Base Clock2230 MHz2280 MHz2210 MHz2310 MHz1920 MHz2310 MHz1830 MHz
Boost Clock2520 MHz2520 MHz2510 MHz2610 MHz2475 MHz2535 MHz2460 MHz
FP32 Compute83 TFLOPsTBD49 TFLOPs40 TFLOPs29 TFLOPs22 TFLOPs15 TFLOPs
RT TFLOPs191 TFLOPsTBD113 TFLOPs82 TFLOPs67 TFLOPs51 TFLOPs35 TFLOPs
Tensor-TOPs1321 TOPsTBD780 TOPs641 TOPs466 TOPs353 TOPs242 TOPs
Memory Capacity24 GB GDDR6X24 GB GDDR6X16 GB GDDR6X12 GB GDDR6X12 GB GDDR6X8-16 GB GDDR68 GB GDDR6
Memory Bus384-bit384-bit256-bit192-bit192-bit128-bit128-bit
Memory Speed21.0 Gbps21.0 Gbps23.0 Gbps21.0 Gbps21.0 Gbps18.0 Gbps17.0 Gbps
Bandwidth1008 GB/s1008 GB/s736 GB/s504 GB/s504 GB/s288 GB/s
(554 GB/s Effective)
272 GB/s
(453 GB/s Effective)
TBP450W425W320W285W200W160-165W115W
Price (MSRP / FE)$1599 US / 1949 EU12,999 RMB (China-Only)$1199 US / 1469 EU$799 US$599 US$399-$499 US$299 US
Price (Current)$1599 US / 1859 EU12,999 RMB (China-Only)$1199 US / 1399 EU$799 US$599 US$399-$499 US$299 US
Launch (Availability)12th October 2022Early 202416th November 20225th January 202313th April 202324th May / 18th July 202329th June 2023

Comments
Welcome to yitit comments! Please keep conversations courteous and on-topic. To fosterproductive and respectful conversations, you may see comments from our Community Managers.
Sign up to post
Sort by
Login to display more comments
Hardware
Recent News
Copyright 2023-2026 - www.yitit.com All Rights Reserved