A January 5, 2023 release date is being mooted by retailers for NVIDIA's upcoming GeForce RTX 4070 Ti graphics card, which is widely expected to be a re-branding of what would have been the RTX 4080 12 GB. Italian retailer Drako started a countdown for an ASUS TUF Gaming RTX 4070 Ti O12G custom-design graphics card, which winds down to January 5, and aligns with the rumored January 3 announcement of the card. It is also expected that reviews of the RTX 4070 Ti will be allowed to go live on January 4.

The GeForce RTX 4080 12 GB was supposed to max out the 4 nm AD104 silicon, featuring 7,680 CUDA cores across 60 SM (streaming multiprocessors), 60 RT cores, 240 Tensor cores, 240 TMUs, and 80 ROPs. The GPU features a 192-bit wide GDDR6X memory interface, to which NVIDIA is giving 21 Gbps-rated memory, yielding 504 GB/s of memory bandwidth. Its most interesting aspect is its power configuration, with a typical board power of 285 W, which makes it technically possible for board partners to use two 8-pin PCIe power connectors, unless they've been asked nicely to implement the 16-pin 12VHPWR connector.

Here's the first picture of the 4 nm "AD104" silicon powering what would have been the $900 GeForce RTX 4080 12 GB, and upcoming RTX 4070-series graphics cards. The third largest GPU based on the "Ada Lovelace" graphics architecture, the AD104 looks tiny. This is because it has roughly half the die-area of the AD102, estimated to be around 295 mm² (compared to 608 mm² of the AD102), which means its transistor count should be less than half, with older reports pinpointing it to 35.8 billion. The RTX 4080 12 GB was supposed to max out the AD104 silicon, enabling all 60 streaming multiprocessors (SM) physically present.

The AD104 with 60 SM hence has 7,680 CUDA cores, 60 RT cores, 240 Tensor cores, 240 TMUs, and 80 ROPs. NVIDIA has generationally narrowed the memory interface (compared to the GA104 and TU104), down to 192-bit GDDR6X. Its predecessors such as the GA104 feature 256-bit wide memory interfaces. NVIDIA is overcoming the memory bus width "deficit" by giving SKUs based on the silicon higher memory speeds (21 Gbps or more); and architecture-level improvements such as larger on-die caches. NVIDIA is reportedly planning to launch an AD104-based SKU early January 2023. VideoCardz reports that could be the RTX 4070 Ti, a re-branding of the RTX 4080 12 GB.

NVIDIA recently updated its product stack with an 8 GB 128-bit GDDR6 variant of the GeForce RTX 3060 (originally 12 GB 192-bit GDDR6), and the RTX 3060 Ti with faster 19 Gbps 256-bit GDDR6X memory (originally 14 Gbps 256-bit GDDR6). We're getting to learn that the new RTX 3060 Ti GDDR6X variant is designed to replace the older GDDR6 variant. NVIDIA's add-in card (AIC) partners are reportedly winding down orders of the original RTX 3060 Ti in favor of the newer GDDR6X variant. Perhaps the most striking aspect of the GDDR6X variant isn't that its memory bandwidth is 35% higher than that of the original RTX 3060 Ti; but that it sells at the same price.

The new GeForce RTX 3060 Ti GDDR6X is based on the 8 nm "GA104" silicon, and has the same core-configuration as the original RTX 3060 Ti, with 4,864 CUDA cores, 152 Tensor cores, 38 RT cores, 152 TMUs, and 80 ROPs; the same GPU boost frequency of 1665 MHz, and interestingly, the same typical board power of 200 W. What's changed is the switch to 19 Gbps GDDR6X memory compared to the original's 14 Gbps GDDR6, which results in a memory bandwidth of 608 GB/s, compared to the original's 448 GB/s.

ASUS today announced new versions of the TUF Gaming GeForce RTX 3060 Ti and the Dual GeForce RTX 3060 Ti graphics cards that now feature GDDR6X memory for greater performance. The NVIDIA GeForce RTX 3060 Ti has been an excellent sweet spot between price and performance for the past generation of graphics cards, and it has now been improved. The GDDR6X memory further boosts the capabilities of the 3060 Ti and expands the options available to the discerning PC DIY builder. ASUS is also updating the GeForce RTX 3060 with a new model featuring 8 GB of GDDR6 VRAM to add even more possibilities for upgrading and assembling.

The ASUS TUF Gaming GeForce RTX 3060 Ti 8 GB GDDR6X features the same triple Axial Tech fan design, solid aluminium backplate, and 2.7-slot form factor as its predecessor, as well as support for NVIDIA G-SYNC and GPU Tweak III. Supplementing that rock-solid foundation is the introduction of GDDR6X ultra-high-speed and error-correcting VRAM, setting up the GPU to deliver more frames per second than the previous iteration. A factory-overclocked version is also available, tuned in-house to make sure users get the absolute best performance right out of the box.

NVIDIA today formally launched the GeForce RTX 4080 graphics card, its second fastest offering from the GeForce "Ada Lovelace" generation. With a starting price of USD $1,200, the card is positioned a notch below the RTX 4090 flagship, a whole $400 cheaper. It is technically supposed to succeed the RTX 3080 12 GB, while an RTX 4080 12 GB variant was supposed to succeed the RTX 3080 10 GB. NVIDIA cancelled the RTX 4080 12 GB as it heaped bad press due to its specs being significantly different from those of the RTX 4080 16 GB, making this the only SKU with the name RTX 4080.

The GeForce RTX 4080 is based on the 4 nm "AD103" silicon, and armed with 9,728 CUDA cores across 76 streaming multiprocessors. It gets 304 4th generation Tensor cores, and 76 RT cores, besides 112 ROPs. Although it has generationally more memory at 16 GB, its memory bus is narrower at 256-bit GDDR6X. NVIDIA attempted to compensate for this with use of faster 22.4 Gbps-rated memory, and architectural improvements such as larger caches on the silicon, to speed up the memory sub-system. NVIDIA is launching not just the Founders Edition card, but also its partners are launching custom-design boards. Every partner's lineup we've come across thus far includes at least one SKU priced at the $1,200 baseline. The cards should be on the shelves tomorrow (November 16, 2022).

We have a large number of reviews for you today, which include the NVIDIA RTX 4080 Founders Edition, ZOTAC RTX 4080 AMP Extreme AIRO, ASUS ROG Strix RTX 4080 OC, MSI RTX 4080 SUPRIM X, Colorful RTX 4080 Ultra White OC, Gainward RTX 4080 Phantom GS, MSI RTX 4080 Gaming X Trio, and the PNY XLR8 RTX 4080 Verto OC

NVIDIA had originally planned to launch the GeForce RTX 4080 16 GB, and the now-cancelled RTX 4080 12 GB in mid-November, but facing strong backlash from the press and social-media over the confusion the "RTX 4080 12 GB" branding would cause due to a vastly different hardware specification to that of the RTX 4080 16 GB (limited not only to the memory size); the company cancelled the launch of the RTX 4080 12 GB. We're hearing that with NVIDIA's board partners already having manufactured a large inventory of RTX 4080 12 GB cards, something had to be done. The partners could be undertaking a rebranding exercise, and the new brand is "GeForce RTX 4070 Ti."

According to kopite7kimi, a reliable source with NVIDIA leaks, the RTX 4080 12 GB will be rebranded as the RTX 4070 Ti. VideoCardz reports that the card is probably bound for a January 2023 launch. Based on the 4 nm "AD104" silicon, the RTX 4080 12 GB was supposed to max out the silicon, featuring 7,680 CUDA cores, 60 RT cores, 240 Tensor cores, 240 TMUs, 80 ROPs, and a 192-bit wide memory interface, running 12 GB of 23 Gbps GDDR6X memory (504 GB/s bandwidth). The RTX 4080 12 GB was originally slated to launch at a USD $900 price-point. It remains to be seen if NVIDIA is bold enough to sell a xx70-class product at $900. AMD is launching the Radeon RX 7900 XT at this price.

Here's the first picture of the PCB of the NVIDIA GeForce RTX 4080 Founders Edition. With NVIDIA cancelling the AD104-based GeForce RTX 4080 12 GB, the significantly buffed, AD103-based RTX 4080 16 GB is now referred to as simply the RTX 4080. The picture reveals an asymmetric PCB shape to fit with the Founders Edition dual-axial flow-through design. The card pulls power from a 16-pin ATX 12VHPWR connector, and appears to use roughly a 16-phase VRM. The PCB has many blank VRM phase traces, although just eight memory-chip pads to go with the 256-bit wide GDDR6X memory interface of the AD103 silicon.

The AD103 silicon features a rectangular die, and a fiberglass substrate that looks about the same size as past-generation NVIDIA GPUs with 256-bit wide memory interfaces, such as the GA104. The AD103 GPU is probably pin-compatible with the smaller AD104, at least as far as substrate-size is concerned; so minimal PCB design R&D effort is put into designing the 12 GB and 16 GB variants of the RTX 4080. The RTX 4080 12 GB is now gone, and the AD104 will power --70 classs SKUs with fewer shaders than what would've been the RTX 4080 12 GB. The display output configuration remains the same as the RTX 4090, with three DisplayPort 1.4a, and an HDMI 2.1a. NVIDIA is expected to launch the GeForce RTX 4080 on November 16, priced at USD $1,199 (MSRP).

NVIDIA today released the latest version of its GeForce Game Ready drivers. Version 526.47 WHQL adds support for two new GPUs, namely the GeForce RTX 3060 8 GB, and the RTX 3060 Ti GDDR6X, the two SKUs NVIDIA launched to improve its standing against the RX 6650 XT, RX 6600, and Arc 7-series. Among the game optimizations with this release are for "Sackboy: A Big Adventure," "Victoria 3," "WRC Generations," and DLSS 3 frame-generation support in F1 22. Among the handful issues fixed with this release are game map corruption in "Cyberpunk 2077," a crash and reboot issue noticed with the Dell XPS 9560; lower performance noticed in Minecraft Java Edition; the 165 Hz refresh-rate option not being available with Samsung Odyssey Ark monitors; GeForce Experience selecting the wrong display-head with Shadowplay; and certain online video artifacting noticed with NVIDIA Image Scaling enabled.

DOWNLOAD: NVIDIA GeForce 526.47 WHQL

NVIDIA manufactured a heap of large "GA102" Ampere silicon to cater to demand from the crypto-mining boom; only to see that demand vanish. With next-gen RTX 40-series awaiting ramp; the company has to digest these GA102 chips somehow, and is apparently letting its partners use them on performance-segment SKUs such as the GeForce RTX 3070 Ti. The RTX 3070 Ti is normally based on the GA104 silicon, which it maxes out, enabling all 6,144 CUDA cores, 48 RT cores, 192 Tensor cores, 192 TMUs, and 96 ROPs, besides the chip's full 256-bit wide GDDR6X memory interface. This SKU is now being carved out on the larger GA102, by enabling 48 out of 84 streaming multiprocessors (just 57% of the CUDA cores enabled); and narrowing the memory bus from its normal 384-bit, down to 256-bit.

The memory size remains at 8 GB, memory type at GDDR6X, and memory speed at 19 Gbps, working out to 608 GB/s of bandwidth. The most interesting aspect of carving the RTX 3070 Ti out of the GA102 has to be board power; with a ZOTAC-branded card listing it at 320 W, higher than the 290 W of GA104-based cards from the company. Sadly, this is a China-only SKU. Every custom-design graphics card, especially from a reputed AIC such as ZOTAC, has to go through qualification with NVIDIA; which means NVIDIA is not only aware of GA102-based RTX 3070 Ti cards, but is behind fusing the SMs to carve out the SKU, and developing the video BIOS and driver support. ZOTAC is kind enough to list the ASIC code on its website, and for this SKU it is "GA102-150-xx."

NVIDIA has decided to cancel the November 2022 launch of the GeForce RTX 4080 12 GB. The company will relaunch the card under a different name, though it didn't announce the replacement name just yet. The naming of the RTX 4080 12 GB was cause for much controversy. With the RTX 40-series "Ada," NVIDIA debuted three SKUs—the already launched RTX 4090 which is in stores right now; the RTX 4080 16 GB, and the RTX 4080 12 GB. Memory size notwithstanding, the RTX 4080 12 GB is a vastly different graphics card from the RTX 4080 16 GB.

The RTX 4080 12 GB and RTX 4080 16 GB didn't even share the same silicon. While the 16 GB model is based on the larger "AD103" silicon, has 9,728 CUDA cores, and a 256-bit wide GDDR6X memory bus; the RTX 4080 12 GB is based on the smaller "AD104" silicon, has just 7,680 CUDA cores (21% fewer CUDA cores); and a meager 192-bit wide GDDR6X memory bus. This had the potential to confuse buyers, especially given the $900 price. With criticism spanning not just social media but also bad press, NVIDIA decided to pull the plug on the RTX 4080 12 GB. The company will likely re-brand it as a successor to the RTX 3070 Ti, although then it will have a hard time justifying its $900 price-tag. The RTX 4080 16 GB, however, is on track for a November 16 availability date, with a baseline price of $1,200.

ASUS Republic of Gamers (ROG) today announced the Strix G35CA, a next-generation desktop gaming PC for Windows 11 powered by the latest 13th Gen Intel Core processors and up to an NVIDIA GeForce RTX 3090 GPU. The motherboard is built on the all-new Intel Z790 chipset, a robust platform with DDR5, PCI Express (PCIe) 4.0 and WiFi 6E support, ensuring that the G35CA will be a high-performance gaming machine for years to come.

ROG Strix machines are built to power high-performance gaming experiences, and the ROG Strix G35CA is no exception—being powered by up to the 24 core 32 thread Intel Core i9-13900KF processor. Built using Intel's Raptor Lake architecture, the CPU uses a mix of high-powered performance cores and energy-friendly but powerful efficiency cores. This CPU is optimized for Windows 11 and can intelligently allocate tasks between the cores to maintain high performance without sacrificing power efficiency, giving users a seamless gaming experience. With maximum boost clocks of up to 5.8 GHz, this processor is the clear choice for gamers who demand the very best hardware.

Here's our first look at the "AD103" and "AD104" chips powering the GeForce RTX 4080 16 GB and RTX 4080 12 GB, respectively, thanks to Ryan Smith from Anandtech. These are the second- and third-largest implementations of the GeForce "Ada" graphics architecture, with the "AD102" powering the RTX 4090 being the largest. Both chips are built on the same TSMC 4N (4 nm EUV) silicon fabrication process as the AD102, but are significantly distant from it in specifications. For example, the AD102 has a staggering 80 percent more number-crunching machinery than the AD103, and a 50 percent wider memory interface. The sheer numbers at play here, enable NVIDIA to carve out dozens of SKUs based on the three chips alone, before we're shown the mid-range "AD106" in the future.

The AD103 die measures 378.6 mm², significantly smaller than the 608 mm² of the AD102, and it reflects in a much lower transistor count of 45.9 billion. The chip physically features 80 streaming multiprocessors (SM), which work out to 10,240 CUDA cores, 320 Tensor cores, 80 RT cores, and 320 TMUs. The chip is endowed with a healthy ROP count of 112, and has a 256-bit wide GDDR6X memory interface. The AD104 is smaller still, with a die-size of 294.5 mm², a transistor count of 35.8 billion, 60 SM, 7,680 CUDA cores, 240 Tensor cores, 60 RT cores, 240 TMUs, and 80 ROPs. Ryan Smith says that the RTX 4080 12 GB maxes out the AD104, which means its memory interface is physically just 192-bit wide.

At the heart of the GeForce RTX 4090 is the gigantic AD102 silicon, which we broadly detailed in an older article. Built on the 4 nm silicon fabrication process, this chip measures 608 mm² in die-area, and crams in 76.3 billion transistors. We now have our first look into the silicon-level block diagram of the AD102, including the introduction of several new components.

The AD102 features a PCI-Express 4.0 x16 host interface, and a 384-bit GDDR6X memory interface. The Gigathread Engine acts as a the main resource allocation component of the silicon. Ada introduces the Optical Flow Accelerator, a component crucial for DLSS 3 to generate entire frames without involving the graphics rendering machinery. The chip features double the number of media-encoding hardware engines as "Ampere," including hardware-accelerated AV1 encode/decode. Multiple accelerators mean that multiple streams of videos can be transcoded (helpful in a media production environment), or transcoding is performed at twice the FPS rate (each encoder takes turns at encoding a single frame).

The AD102 silicon on which NVIDIA's new flagship graphics card, the GeForce RTX 4090, is based, is a marvel of semiconductor engineering. Built on the 4 nm EUV (TSMC 4N) silicon fabrication process, the chip has a gargantuan transistor-count of 76.3 billion, a nearly 170% increase over the previous GA102, and a die-size of 608 mm², which is in fact smaller than the 628 mm² die-area of the GA102. This is thanks to TSMC 4N offering nearly thrice the transistor-density of the Samsung 8LPP node on which the GA102 is based.

The AD102 physically features 18,432 CUDA cores, 568 fourth-generation Tensor cores, and 142 third-generation RT cores. The streaming multiprocessors (SM) come with special components that enable the Shader Execution Reordering optimization, which has a significant performance impact on both raster- and ray traced graphics rendering performance. The silicon supports up to 24 GB of GDDR6X or up to 48 GB of GDDR6+ECC memory (the latter will be seen in the RTX Ada professional-visualization card), across a 384-bit wide memory bus. There are 568 TMUs, and a mammoth 192 ROPs on the silicon.

Amid the fog of rapid announcements and AIC graphics card launches, this little, interesting detail might have missed you, but the new GeForce RTX 4080 12 GB graphics card announced yesterday; features a memory bus-width of just 192-bit, which is half that of the RTX 3080 12 GB (384-bit). The card uses 21 Gbps GDDR6X memory, which at 192-bit bus-width, works out to just 504 GB/s bandwidth. In comparison, the RTX 3080 12 GB uses 19 Gbps GDDR6X memory, which at 384-bit bus width, produces 912 GB/s. In fact, even the original RTX 3080 with 10 GB of GDDR6X memory across a 320-bit bus, has 760 GB/s on tap.

The bigger RTX 4080 16 GB variant uses 256-bit memory bus, but faster 23 Gbps GDDR6X memory, producing 736 GB/s of memory bandwidth, which again, is less than that of the original 10 GB RTX 3080. It's only the RTX 4090 that has an unchanged amount of memory bandwidth over the previous generation—1008 GB/s, which is identical to that of the RTX 3090 Ti, and a tad higher than the 936 GB/s of the RTX 3090 (non-Ti). Of course, memory bandwidth is no way to compare the RTX 40-series from its predecessors, there are a dozen other factors that weigh into performance, and what matters is you're getting generationally more memory amounts with the RTX 4080-series. The RTX 4080 12 GB offers 20% more memory than the RTX 3080, and the RTX 4080 16 GB offers 33% more than the RTX 3080 12 GB. NVIDIA tends to deliver significant performance gains with each new generation, and we expect this to hold up.

NVIDIA today unveiled the GeForce RTX 40 Series of GPUs, designed to deliver revolutionary performance for gamers and creators, led by its new flagship, the RTX 4090 GPU, with up to 4x the performance of its predecessor. The world's first GPUs based on the new NVIDIA Ada Lovelace architecture, the RTX 40 Series delivers massive generational leaps in performance and efficiency, and represents a new era of real-time ray tracing and neural rendering, which uses AI to generate pixels.

"The age of RTX ray tracing and neural rendering is in full steam, and our new Ada Lovelace architecture takes it to the next level," said Jensen Huang, NVIDIA's founder and CEO, at the GeForce Beyond: Special Broadcast at GTC. "Ada provides a quantum leap for gamers and paves the way for creators of fully simulated worlds. With up to 4x the performance of the previous generation, Ada is setting a new standard for the industry," he said.

When we first got news about NVIDIA's upcoming GeForce RTX 4080 "Ada" coming in 12 GB and 16 GB variants, we knew there was more setting the two apart than just memory size and memory bus-width. Turns out there's a lot more. According to detailed specifications leaked to the web, while the 16 GB variant of the RTX 4080 is based on the same AD103, the second largest chip after the AD102; the 12 GB RTX 4080 is based on the smaller AD104 chip which has a physically narrower memory bus.

It looks like NVIDIA is debuting the RTX 40-series with at least three models—RTX 4090 24 GB, RTX 4080 16 GB, and RTX 4080 12 GB. The RTX 4090 is the top-dog part, with the ASIC code "AD102-300-xx." It's endowed with 16,384 CUDA cores, a boost frequency of up to 2.52 GHz, 24 GB of 21 Gbps GDDR6X memory, and a typical graphics power (TGP) of 450 W, which is "configurable" up to 600 W. The RTX 4080 16 GB is based on the AD103-300-xx" comes with 9,728 CUDA cores, a boost frequency of 2.50 GHz, and 16 GB of 23 Gbps GDDR6X memory across a narrower memory bus than the one the RTX 4090 comes with. This card reportedly has a 340 W TGP configurable up to 516 W.

NVIDIA has a leaky tap to fix with the part of the supply chain that makes retail boxes for its next-gen graphics cards. After last weekend's leak of the ZOTAC RTX 4090, we now have one of the GIGABYTE RTX 4090 Gaming OC. It confirms the new typeface NVIDIA is using for the main branding of its RTX 40-series. The card itself features a mammoth triple-slot (possibly even quad-slot) cooling solution that's almost 1.5x what constitutes "full-height" for add-on cards. The box art also confirms 24 GB GDDR6X as the memory configuration of the RTX 4090. NVIDIA is expected to unveil the RTX 40-series next week at GTC; with retail availability from early-Q4 2022.

Two sets of possible specifications of the upcoming performance-segment NVIDIA GeForce RTX 4070 "Ada" graphics card has hit the rumor-mill, according to kopite7kimi, a reliable source with NVIDIA leaks. The first set of specs sees the card feature 12 GB of 21 Gbps GDDR6X memory (possibly over a 192-bit wide memory bus), as many as 7,680 CUDA cores, a typical board power of 285 W, and an internal SKU code of "PG141-SKU340/341." It makes sense for 12 GB of memory across a 192-bit memory bus to be a logical choice for NVIDIA (as opposed to the previous-gen RTX 3070 with its 8 GB of 14 Gbps GDDR6 across 256-bit); as it allows the company to achieve a 50% memory size increase gen-over-gen, while reducing the number of memory chips on the card from 8 to 6 (by using six 16 Gbit GDDR6X chips).

The second set of specs doing rounds is the "PG141-SKU336/337," consisting of 7,168 CUDA cores, 10 GB of 21 Gbps GDDR6X memory across what we're assuming could be a 160-bit wide memory bus (five memory chips), and 250 W typical board power. The same source also claims that the SKU340/341 could have a performance target of over 11000 points in Time Spy Extreme, while the SKU336/337 could be designed with at least 10000 points in mind. It's quite possible that the second configuration is that of the RTX 3060 Ti-successor SKU. Given NVIDIA's top-down approach to product launches, we could expect performance-segment SKUs only toward the end of 2022, or early-2023.

NVIDIA's upcoming GeForce RTX 40 series graphics cards are less than two months from the official launch. As we near the final specification draft, we are constantly getting updates from hardware leakers claiming that the specification is ever-changing. Today, @kopite7kimi has updated his GeForce RTX 4080 GPU predictions with some exciting changes. First off, the GPU memory will get an upgrade over the previously believed specification. Before, we thought that the SKU used GDDR6X running at 21 Gbps; however, now, it is assumed that it uses a 23 Gbps variant. Faster memory will definitely result in better overall performance, and we are yet to see what it can achieve with overclocking.

Next, another update for NVIDIA GeForce RTX 4080 comes with the SKU's total board power (TBP). Previously we believed it came with a 420 Watt TBP; however, the sources of kopite7kimi claim that it has a 340 Watt TBP. This 60 Watt reduction is rather significant and could be attributed to NVIDIA's optimization to have the most efficient design possible.

Memory giant Micron Technology has commenced mass-production of 21 Gbps and 24 Gbps-rated GDDR6X memory chips that will be exclusively used by NVIDIA in its next-generation RTX 40-series "Ada" graphics cards. GDDR6X is a derivative of GDDR6 co-developed by NVIDIA and Micron, which leverages PAM4 signaling to increase data-rates. Depending on the graphics card model, NVIDIA will use 8 Gbit (1 GB) or 16 Gbit (2 GB) density memory chips. We're hearing that 21 Gbps will be the standard data-rate used by SKUs that succeed the RTX 3080 and RTX 3080 Ti; while 24 Gbps will be used by the faster RTX 3090/Ti successors. The part numbers of these memory chips are listed below.

NVIDIA's upcoming GeForce RTX 40 series Ada Lovelace graphics card lineup is slowly shaping up to be a significant performance uplift compared to the previous generation. Today, according to a well-known hardware leaker kopite7kimi, we are speculating that a mid-range AD104 SKU could match the performance of the last-generation flagship GeForce RTX 3090 Ti graphics card. The full AD104 SKU is set to feature 7680 FP32 CUDA cores, paired with 12 GB of 21 Gbps GDDR6X memory running on a 192-bit bus. Coming with a large TGP of 400 Watts, it should have a performance of the GA102-350-A1 SKU found in GeForce RTX 3090 Ti.

Regarding naming this complete AD104 SKU, it should end up as a GeForce RTX 4070 Ti model. Of course, we must wait and see what NVIDIA decides to do with the lineup and what the final models will look like.

An alleged technical drawing of the PCB of reference-design NVIDIA "Ada" AD102 silicon was leaked to the web, courtesy of Igor's Lab. It reveals a large GPU pad that's roughly the size of the GA102 (the size of the fiberglass substrate or package, only, not the die); surrounded by twelve memory chips, which are likely GDDR6X. There are also provision for at least 24 power phases, although not all of them are populated by sets of chokes and DrMOS in the final products (a few of them end up vacant).

We also spy the 16-pin ATX 3.0 power connector that's capable of delivering up to 600 W of power; and four display outputs, including a USB-C in lieu of a larger connector (such as DP or HDMI). A curious thing to note is that the card continues to have an NVLink connector. Multi-GPU is dead, which means the NVLink on the reference design will likely be rudimentary in the GeForce RTX product (unless used for implicit multi-GPU). The connector may play a bigger role in the professional-visualization graphics cards (RTX AD-series) based on this silicon.

NVIDIA's next-generation GeForce RTX 40 series of graphics cards, codenamed Ada Lovelace, is shaping up to be a powerful graphics card lineup. Allegedly, we can expect to see a mid-July launch of NVIDIA's newest gaming offerings, where customers can expect some impressive performance. According to a reliable hardware leaker, kopite7kimi, NVIDIA GeForce RTX 4090 graphics card will feature AD102-300 GPU SKU. This model is equipped with 126 Streaming Multiprocessors (SMs), which brings the total number of FP32 CUDA cores to 16128. Compared to the full AD102 GPU with 144 SMs, this leads us to think that there will be an RTX 4090 Ti model following up later as well.

Paired with 24 GB of 21 Gbps GDDR6X memory, the RTX 4090 graphics card has a TDP of 450 Watts. While this number may appear as a very power-hungry design, bear in mind that the targeted performance improvement over the previous RTX 3090 model is expected to be a two-fold scale. Paired with TSMC's new N4 node and new architecture design, performance scaling should follow at the cost of higher TDPs. These claims are yet to be validated by real-world benchmarks of independent tech media, so please take all of this information with a grain of salt and wait for TechPowerUp reviews once the card arrives.

Only a week ago the first pictures of the ASUS x Noctua GeForce RTX 3080 card turned up on the web and now the card has been officially announced as the ASUS GeForce RTX 3080 Noctua OC Edition 10 GB GDDR6X. The card will have an OC and a Gaming mode with different boost clocks, where the Gaming mode allows the GPU to boost to 1785 MHz and the OC mode takes this further to 1815 MHz. The memory remains at stock clocks and uses 19 Gbps GDDR6X memory. ASUS claims it's the quietest card in its class, but doesn't mention any actual noise levels, although the card comes with a 0dB fan stop mode. It should be noted that the card takes up 4.1 slots and as such, it might not fit in all builds. No official pricing was provided.