An Ebay Store—customgpu_official—is selling memory modified GeForce RTX 2080 Ti graphics cards. The outfit (located in Palo Alto, California) has a large inventory of MSI GeForce RTX 2080 Ti AERO cards—judging from their listing's photo gallery. Workers in China are reportedly upgrading these (possibly refurbished) units with extra lashings of GDDR6 VRAM—going from the original 11 GB specification up to 22 GB. We have observed smaller scale GeForce RTX 2080 Ti modification projects and a very ambitious user-modified example in the past, but customgpu's latest endeavor targets a growth industry—the item description states: "Why do you need a 22 GB 2080 Ti? Large VRAM is essential to cool AIGC apps such as stable diffusion fine tuning, LLAMA, LLM." At the time of writing three cards are available to purchase, and interested customers have already acquired four memory modded units.

They advertise their upgraded "Turbo Edition" card as a great "budget alternative" to more modern GeForce RTX 3090 and 4090 models—"more information and videos" can be accessed via 2080ti22g.com. The MSI GeForce RTX 2080 Ti AERO 11 GB model is not documented within TPU's GPU database, but its dual-slot custom cooling solution is also sported by the MSI RTX 2080 SUPER AERO 8 GB graphics card. The AERO's blower fan system creates a "mini-wind tunnel, pulling fresh air from inside the case and blowing it out the IO panel, and out of the system." The seller's asking price is $499 per unit—perhaps a little bit steep for used cards (potentially involved in mining activities), but customgpu_official seems to be well versed in repairs. Other Ebay listings show non-upgraded MSI GeForce RTX 2080 Ti AERO cards selling in the region of $300 to $400. Custom GPU Upgrade and Repair's hype video proposes that their modified card offers great value, given that it sells for a third of the cost of a GeForce RTX 3090—their Ebay item description contradicts this claim: "only half price compared with GeForce RTX 3090 with almost the same GPU memory."

MSI has recently launched the first NVIDIA Cryptocurrency Mining Processor (CMP) 50HX model with the MSI CMP 50HX MINER. The CMP 50HX is the third card in the CMP lineup above the CMP 30HX and CMP 40HX and a step below the flagship as of yet unreleased CMP 90HX. The CMP 50HX was expected to feature nearly identical specifications to the RTX 2080 Ti due to the similar reported mining performance and the fact that 30HX and 40HX models were derived from consumer cards. MSI has revealed that the CMP 50HX does use the TU102 but with only 3584 CUDA core compared to the 4352 cores found with the RTX 2080 Ti, the 50HX also features less memory with only 10 GB GDDR6. These core and memory reductions do come with a small power requirement reduction from 250 W to 225 W however dual 8-pin power connectors are still required. The MSI CMP 50HX card features a blower cooler design with a small plastic window and no display outputs.

Have you ever wondered if your graphics card could pack just a little bit more VRAM than it is advertised to come with? Well, if you have some spare time and some awesome soldering skills, you could find out yourself by placing higher-capacity VRAM chips in place of the standard memory. That is exactly what VIK-on, a hardware modder from Russia, has done with his graphics cards. Before, VIK-on modded the NVIDIA GeForce RTX 2070 to support 16 GB of GDDR6 memory and modded NVIDIA's GeForce RTX 3070 to also support 16 GB of GDDR6 memory. Today, VIK-on has done it again and the modder has tested his skills by proving that it is possible to install 22 GB of GDDR6 memory on the GeForce RTX 2080 Ti graphics card.

The modder has taken a broken NVIDIA GeForce RTX 2080 Ti GPU that was in very bad condition. He had to re-solder the GPU and fix some broken PCB traces. Finally, after that, he tried to install more VRAM than the card came with in the first place. The TU102 SKU is capable of handling up to 48 GB of VRAM, as seen with Quadro RTX 8000 GPU. However, the problem would be firmware support. VIK-on used a strap mod, leading the GPU BIOS to believe that there is much more memory present compared to the stock version, and the card managed to boot. However, some screen flickering was present and it had stability issues, so the mod isn't very successful.

Here's the first picture of an NVIDIA "Ampere" GA102 GPU die. This is the largest client-segment implementation of the "Ampere" architecture by NVIDIA, targeting the gaming (GeForce) and professional-visualization (Quadro) market segments. The "Ampere" architecture itself debuted earlier this year with the A100 Tensor Core scalar processor that's winning hearts and minds in the HPC community faster than ice cream on a dog day afternoon. There's no indication of die-size, but considering how tiny the 10.3 billion-transistor AMD "Navi 10" die is, the GA102 could come with a massive transistor count if its die is as big as that of the TU102. The GPU in the picture is also a qualification sample, and was probably pictured off a prototype graphics card. Powering the GeForce RTX 3090, the GA102-300 is expected to feature a CUDA core count of 5,248. According to VideoCardz, there's a higher trim of this silicon, the GA102-400, which could make it to NVIDIA's next halo product under the TITAN brand.

AMD is developing a larger GPU based on its new "Navi" architecture to power a new high-end graphics card family, likely the Radeon RX 5800 series. The codename "Navi 12" is doing rounds on social media through familiar accounts that have high credibility with pre-launch news and rumors. The "Navi 10" silicon was designed to compete with NVIDIA's "TU106," as its "XT" and "Pro" variants outperform NVIDIA's original RTX 2060 and RTX 2070, forcing it to develop the RTX 20 Super series, by moving up specifications a notch.

Refreshing its $500 price-point was particularly costly for NVIDIA, as it was forced to tap into the 13.6 billion-transistor "TU104" silicon to carve out the RTX 2070 Super; while for the RTX 2060 Super, it had to spend 33 percent more on the memory chips. With the "Navi 12" silicon, AMD is probably looking to take a swing at NVIDIA's "TU104" silicon, which has been maxed out by the RTX 2080 Super, disrupting the company's $500-700 lineup once again, with its XT and Pro variants. There's also a remote possibility of "Navi 12" being an even bigger chip, targeting the "TU102."

NVIDIA's SUPER teaser hasn't crystallized into something physical as of now, but we know it's coming - NVIDIA themselves saw to it that our (singularly) collective minds would be buzzing about what that teaser meant, looking to steal some thunder from AMD's E3 showing. Now, that teaser seems to be coalescing into something amongst the industry: an entire lineup upgrade for Turing products, with NVIDIA pulling their chips up one rung of the performance chair across their entire lineup.

Apparently, NVIDIA will be looking to increase performance across the board, by shuffling their chips in a downward manner whilst keeping the current pricing structure. This means that NVIDIA's TU106 chip, which powered their RTX 2070 graphics card, will now be powering the RTX 2060 SUPER (with a reported core count of 2176 CUDA cores). The TU104 chip, which power the current RTX 2080, will in the meantime be powering the SUPER version of the RTX 2070 (a reported 2560 CUDA cores are expected to be onboard), and the TU102 chip which powered their top-of-the-line RTX 2080 Ti will be brought down to the RTX 2080 SUPER (specs place this at 8 GB GDDR6 VRAM and 3072 CUDA cores). This carves the way for an even more powerful SKU in the RTX 2080 Ti SUPER, which should be launched at a later date. Salty waters say the RTX 2080 Ti SUPER will feature and unlocked chip which could be allowed to convert up to 300 W into graphics horsepower, so that's something to keep an eye - and a power meter on - for sure. Less defined talks suggest that NVIDIA will be introducing an RTX 2070 Ti SUPER equivalent with a new chip as well.

EK Water Blocks, the Slovenia based water cooling gear manufacturer, is introducing its new generation water blocks for the popular ROG Strix GeForce RTX series graphics cards, based on Turing TU106, Turing TU104 and Turing TU102 graphics processor.

The inspiration for the new GPU block name "Vector" came from the sheer computing power of the graphics cards that are on the market today. Naming a water block "Full Cover" isn't enough these days, when the product is packed with unique features, such as these. The EK Vector Strix RTX water blocks are specially designed for multiple ROG Strix GeForce RTX Turing based graphics cards. The water block itself uses the signature EK single slot slim look, and it covers the entire PCB length. This sophisticated cooling solution will transform your powerful ROG graphics card into a minimalistic, elegant piece of hardware with accented RGB LED lighting. The block also features a unique aesthetic cover over the block Terminal which is designed to showcase the graphics card model via LEDs, visible from the side.

After some leaks indicated that GIGABYTE was preparing a blower-style RTX 2080 Ti, the company has now officially unveiled it. The GIGABYTE AORUS Turbo RTX 2080 Ti feature a blower-style cooler with vapor-chamber, direct-touch technology trying to keep that monstrous, 754 mm² TU102 chip cool and quiet. Luckily, the chip is relatively power efficient, so the acoustic and thermal performance should be sufficient.

The GIGABYTE AORUS Turbo RTX 2080 Ti features a 1650 MHz core clock, and the other specs line up with what we've become used to with RTX 2080 Ti graphics cards (11 GB of GDDR6 memory at 14000 MHz). There's the typical 3x DisplayPort, 1x HDMI, and 1x USB Type-C for VirtuaLink. Expect this version of the RTX 2080 Ti to be near the bottom rung in terms of pricing, when it's available.

With NVIDIA's GeForce RTX 20-series having already released for desktops, it was only a matter of time until laptops got the RTX treatment as well. Current rumors are suggesting that Nvidia will officially launch their GeForce RTX 20-series mobility GPUs on January 6th at CES with the RTX 2070 and RTX 2070 Max-Q taking center stage. An embargo date of January 26th has also been set, with NVIDIA delaying their final release drivers until then. Meaning final performance results for the new mobile GPUs won't be available until after the embargo date, which should coincide with the general availability of RTX 20-series equipped laptops.

Along with the RTX 2070 and 2070 Max-Q mobility parts, the flagship RTX 2080 Max-Q which isn't expected at the show, is still in the works, with its TU104M 1eab device ID having been leaked earlier. The rest of the GeForce 20-series mobility GPUs are likely to use the GTX moniker if NVIDIA's desktop lineup is anything to go by; however, that is merely speculation at this point.

NVIDIA is ready with its new flagship halo consumer graphics card, the TITAN RTX. Several video bloggers such as LinusTechTips have apparently already been sampled with this card, and are probably under NDA not to reveal specifications. Given that "Turing" is the only NVIDIA architecture capable of RTX, NVIDIA could be building the TITAN RTX on the largest "TU102" silicon. The GeForce RTX 2080 Ti does not max out this silicon, leaving NVIDIA room to do so with the TITAN RTX.

A maxed out "TU102" should feature 4,608 CUDA cores, 288 TMUs, 96 ROPs, in addition to 576 tensor cores and 72 RT cores. NVIDIA could also max out the 384-bit wide GDDR6 memory bus, and equip the TITAN RTX with 12 GB of video memory. Using 14 Gbps GDDR6 memory chips, NVIDIA can achieve 672 GB/s of memory bandwidth. The TITAN RTX card itself looks similar to the RTX 2080 Ti Founders Edition graphics card, but with an illuminated "TITAN" logo on top. The card still draws power from a pair of 8-pin PCIe power connectors, and it's likely that NVIDIA is using the same PCB, perhaps with additional capacitors. Pricing and availability is anyone's guess. Given that the RTX 2080 Ti Founders Edition was launched at $1,200, we agree with some of our community members' speculation that $1,800-2,000 doesn't seem implausible.

Update Dec 3: The Titan RTX has launched now for $2,499.

NVIDIA opened up its "Turing" based Quadro RTX 6000 and RTX 5000 graphics cards up for pre-order on its website. The RTX 6000 is priced at USD $6,300, and a quantity limitation of 5 per customer is in place. The RTX 5000, on the other hand, is priced at $2,300, and is out of stock at the time of this writing. The RTX 6000 maxes out the TU102 silicon with 4,608 CUDA cores, 576 Tensor cores, 72 RT cores, and is armed with 24 GB of GDDR6 memory, across the chip's full 384-bit memory bus width, making it the cheapest graphics card that maxes out the silicon, unless NVIDIA comes up with a "TITAN X Turing." The Quadro series comes with an enterprise feature-set and certifications for major content-creation applications not available on the GeForce series.

The Quadro RTX 5000, on the other hand, maxes out the TU104 silicon with 3,072 CUDA cores, 384 Tensor cores, 48 RT cores, and 16 GB of GDDR6 memory across the chip's 256-bit wide memory interface. The $10,000 RTX 8000, which isn't open to pre-orders yet, arms the TU102 with a whopping 48 GB of memory, and higher clocks than the RTX 6000. NVIDIA debuted the "Turing" graphics architecture with the Quadro RTX series a week before the new GeForce RTX 20-series.

While working on GPU-Z support for NVIDIA's RTX 20-series graphics cards, we noticed something curious. Each GPU model has not one, but two device IDs assigned to it. A device ID is a unique identification that tells Windows which specific device is installed, so it can select and load the relevant driver software. It also tells the driver, which commands to send to the chip, as they vary between generations. Last but not least, the device ID can be used to enable or lock certain features, for example in the professional space. Two device IDs per GPU is very unusual. For example, all GTX 1080 Ti cards, whether reference or custom design, are marked as 1B06. Titan Xp on the other hand, which uses the same physical GPU, is marked as 1B02. NVIDIA has always used just one ID per SKU, no matter if custom-design, reference or Founders Edition.

We reached out to industry sources and confirmed that for Turing, NVIDIA is creating two device IDs per GPU to correspond to two different ASIC codes per GPU model (for example, TU102-300 and TU102-300-A for the RTX 2080 Ti). The Turing -300 variant is designated to be used on cards targeting the MSRP price point, while the 300-A variant is for use on custom-design, overclocked cards. Both are the same physical chip, just separated by binning, and pricing, which means NVIDIA pretests all GPUs and sorts them by properties such as overclocking potential, power efficiency, etc.

We are all still awaiting how NVIDIA's RTX 2000 series of GPUs will fare in independent reviews, but that has not stopped the rumor mill from extrapolating. There have been alleged leaks of the RTX 2080 Ti's performance and now we see HWiNFO add support to an unannounced NVIDIA Turing microarchitecture chip, the TU106. As a reminder, the currently announced members in RTX series are based off TU102 (RTX 2080 Ti), and TU104 (RTX 2080, RTX 2070). It is logical to expect a smaller die for upcoming RTX cards based on NVIDIA's history, and we may well see an RTX 2060 using the TU106 chip.

This addition to HWiNFO is to be taken with a grain of salt, however, as they have been wrong before. Even recently, they had added support for what, at the time, was speculated to be NVIDIA Volta microarchitecture which we now know as Turing. This has not stopped others from speculating further, however, as we see 3DCenter.org give their best estimates on how TU106 may fare in terms of die size, shader and TMU count, and more. Given that TSMC's 7 nm node will likely be preoccupied with Apple iPhone production through the end of this year, NVIDIA may well be using the same 12 nm FinFET process that TU102 and TU104 are being manufactured on. This mainstream GPU segment is NVIDIA's bread-and-butter for gross revenue, and so it is possible we may see an announcement with even retail availability towards the end of Q4 2018 to target holiday shoppers.

EK Water Blocks, the Slovenia based water cooling gear manufacturer, is introducing its new generation of high-performance water blocks for the newly announced NVIDIA GeForce RTX series graphics cards, based on Turing TU104 and Turing TU102 graphics processor. The inspiration for the new GPU block name "Vector" came from the sheer computing power of the graphics cards that are on the market today. Naming a water block "Full Cover" isn't enough these days, when the product is packed with unique features, such as these.

The EK Vector RTX water block is specially designed for multiple NVIDIA GeForce RTX Turing based reference design graphics cards. The water block itself uses the signature EK single slot slim look, and it covers the entire PCB length. This sophisticated cooling solution will transform your beefy graphics card into a minimalist, elegant piece of a hardware. The block also features a unique aesthetic cover over the block Terminal which is designed to reveal the graphics card model, visible from the side.

The GeForce RTX 2080 Ti is indeed based on an ASIC codenamed "TU102." NVIDIA was referring to this 775 mm² chip when talking about the 18.5 billion-transistor count in its keynote. The company also provided a breakdown of its various "cores," and a block-diagram. The GPU is still laid out like its predecessors, but each of the 72 streaming multiprocessors (SMs) packs RT cores and Tensor cores in addition to CUDA cores.

The TU102 features six GPCs (graphics processing clusters), which each pack 12 SMs. Each SM packs 64 CUDA cores, 8 Tensor cores, and 1 RT core. Each GPC packs six geometry units. The GPU also packs 288 TMUs and 96 ROPs. The TU102 supports a 384-bit wide GDDR6 memory bus, supporting 14 Gbps memory. There are also two NVLink channels, which NVIDIA plans to later launch as its next-generation multi-GPU technology.

Here are some of the first pictures of NVIDIA's GeForce RTX 2080 Ti ASIC, probably codenamed "TU102." GamersNexus took a ruler to this chip, and discovered that it's one of the biggest non-storage chips in existence. The rectangular die measures 31 mm x 25 mm, or 775 mm². The package has no IHS, but a metal brace along the periphery of the fiberglass substrate distributes mounting pressure from the cooler. NVIDIA is building the "Turing" family of GPUs on TSMC 12 nm FinFET node.

Colorful Technology Company Limited, professional manufacturer of graphics cards, motherboards and high-performance storage solutions, adds two new cards into its AD series, which were named as iGame GeForce RTX 2080 Ti Advanced OC and iGame GeForce RTX 2080 Advanced OC.

The new NVIDIA GeForce RTX GPUs have reinvented graphics and set a new bar for performance. Powered by the new NVIDIA Turing GPU architecture and the revolutionary NVIDIA RTX platform, the new graphics cards bring together real-time ray tracing, artificial intelligence, and programmable shading. This is not only a whole new way to experience games - this is the ultimate PC gaming experience.

The new GPUs were unveiled at a special NVIDIA two-day event called the "GeForce Gaming Celebration" which kicked off on August 20th at the Palladium in Cologne, Germany ahead of Gamescom 2018.

GALAX spilled the beans on the specifications of two of NVIDIA's upcoming high-end graphics cards, as it's becoming increasingly clear that the company could launch the GeForce RTX 2080 and the GeForce RTX 2080 Ti simultaneously, to convince GeForce "Pascal" users to upgrade. The company's strategy appears to be to establish 40-100% performance gains over the previous generation, along with a handful killer features (such as RTX, VirtuaLink, etc.,) to trigger the upgrade-itch.

Leaked slides from GALAX confirm that the RTX 2080 will be based on the TU104-400 ASIC, while the RTX 2080 Ti is based on the TU102-300. The RTX 2080 will be endowed with 2,944 CUDA cores, and a 256-bit wide GDDR6 memory interface, holding 8 GB of memory; while the RTX 2080 Ti packs 4,352 CUDA cores, and a 352-bit GDDR6 memory bus, with 11 GB of memory. The memory clock on both is constant, at 14 Gbps. The RTX 2080 has its TDP rated at 215W, and draws power from a combination of 6-pin and 8-pin PCIe power connectors; while the RTX 2080 Ti pulls 250W TDP, drawing power through a pair of 8-pin PCIe power connectors. You also get to spy GALAX' triple-fan non-reference cooling solution in the slides below.