When NVIDIA announced its next-generation GeForce RTX 3080 and 3090 Ampere GPUs, it specified that the memory found in the new GPUs will be Micron's GDDR6X variant with 19 Gbps speed. However, being that there are faster GDDR6X modules already available in a 21 Gbps variant, everyone was left wondering why NVIDIA didn't just use the faster memory from Micron. That is exactly what Igor's Lab, a technology website, has been wondering as well. They have decided to conduct testing with an infrared camera that measures the heat produced. To check out the full testing setup and how they tested everything, you can go here and read it, including watching the video embedded.

Micron chips like GDDR5, GDDR5X, and GDDR6 are rated for the maximum junction temperature (TJ Max) of 100 degrees Celsius. It is recommended that these chips should run anywhere from 0C to 95C for the best results. However, when it comes to the new GDDR6X modules found in the new graphics cards, they are not yet any official specifications available to the public. Igor's Lab estimates that they can reach 120C before they become damaged, meaning that TJ Max should be 110C or 105C. When measuring the temperature of GDDR6X modules, Igor found out that the hottest chip ran at 104C, meaning that the chips are running pretty close to the TJ Max they are (supposedly) specified. It is NVIDIA's PCB design decisions that are leading up to this, as the hottest chips are running next to voltage regulators, which can get pretty hot on their own.

GIGABYTE today rolled out a trio of custom-design graphics cards that implement the new GDDR5X memory equipped variant of NVIDIA GeForce GTX 1060 6 GB. The lineup begins with the GTX 1060 6 GB D5X WindForce 2X OC (model: GV-N1060WF2OC-6GD 2.0), and goes on to the better-endowed GTX 1060 6 GB D5X WindForce 3X OC (GV-N1060WF3OC-6GD 2.0), and the range-topping GTX 1060 6 GB D5X G1.Gaming OC (GV-N1060G1 GAMING-6GD 3.0).

Out of the box, the D5X WindForce 2X OC offers clock speeds of 1556 MHz GPU core, and 1771 MHz GPU Boost, against NVIDIA-reference speeds of 1506/1708 MHz. The D5X WindForce 3X OC has the same exact clock speeds out of the box, but is endowed with a better WindForce 3X triple-fan cooler that helps sustain boost frequencies and manually overclocked speeds better. The D5X G1.Gaming tops the range with 1594 MHz core and 1809 MHz GPU Boost. Sadly all three cards run the GDDR5X memory at 8.00 GHz clock speeds. All three cards make do with a single 8-pin PCIe power input. Prices (MSRP) range from $249.99 for the WindForce 2X OC to $269.99 for the WindForce 3X OC, and $299.99 for the G1.Gaming OC.

It looks like NVIDIA bought itself a mountain of unsold GDDR5X memory chips, and is now refreshing its own mountain of unsold GP104 inventory, to make products more presentable to consumers in the wake of its RTX 20-series and real-time ray-tracing lure. First, it was the GP104-based GTX 1060 6 GB with GDDR5X memory, and now it's the significantly faster GeForce GTX 1070, which is receiving the newer memory, along with otherwise unchanged specifications. ZOTAC is among the first NVIDIA add-in card partners ready with one such cards, the GTX 1070 AMP Extreme Core GDDR5X (model: ZT-P10700Q-10P).

Much like the GTX 1060 6 GB GDDR5X, this otherwise factory-overclocked ZOTAC card sticks to a memory clock speed of 8.00 GHz, despite using GDDR5X memory chips that are rated for 10 Gbps. It features 8 GB of it across the chip's full 256-bit memory bus width. The GPU is factory-overclocked by ZOTAC to tick at 1607 MHz, with 1797 MHz GPU Boost, which are below the clock-speeds of the GDDR5 AMP Extreme SKU, that has not just higher 1805 MHz GPU Boost frequency, but also overclocked memory at 8.20 GHz. Out of the box, this card's performance shouldn't be distinguishable from the GDDR5 AMP Core, but the memory alone should serve up a significant overclocking headroom.

MSI rolled out one of the many upcoming silently-launched GeForce GTX 1060 6 GB graphics cards to feature the more advanced GDDR5X memory. NVIDIA is designing this SKU to compete with AMD's recently launched Radeon RX 590. Its specifications are very similar to those of the original GTX 1060 6 GB, but GDDR5X lends additional overclocking headroom. NVIDIA is carving this SKU out of the larger GP104 silicon, instead of GP106. You still only get 1,280 CUDA cores, 80 TMUs, 48 ROPs, and a 192-bit wide memory interface.

The MSI Armor OC ships with 1544 MHz GPU clocks, with 1759 MHz GPU Boost frequencies, compared to 1506/1709 MHz reference clock speeds. This factory-overclock is identical to the one the company's original GP106-based Armor OCV1 card ships with. The memory, surprisingly remains at 8.00 GHz, even though we suspect 10 Gbps-rated GDDR5X memory chips are being used in this card. The card draws power from a combination of 6-pin and 8-pin PCIe power connectors. The company's GTX 1060 6 GB Armor OCV1 graphics card only features a single 8-pin. Apparently you get SLI support. The company didn't reveal pricing.

NVIDIA has just shown us one of the most ingenious ways of creating new custom, competitive SKUs for the midrange market without spending any additional amounts of money on R&D, wiring, or memory controller work: just reuse the chips that already have that work done. This is the case for NVIDIA's new GTX 1060 GDDR5X graphics card, which the company has "designed" to further fill in the gaps on its midrange offerings against a revamped Radeon RX 590.

NVIDIA is rushing in a new variant of its GeForce GTX 1060 6 GB graphics card to counter AMD's Radeon RX 590, in a bid to reinforce the $250 price-point ahead of the crucial Holiday season. According to specifications of the GTX 1060 6 GB GDDR5X put out by Palit, the GDDR5X version is a little more than a marketing stunt, with something in there for overclockers. The GTX 1060 GamingPro OC+ from Palit is by no means a "baseline" product. It features 6 GB of GDDR5X memory, which ticks at 8800 MHz (GDDR5X effective), and continues to have a 192-bit wide memory interface. At this speed, the GPU ends up with 211.2 GB/s of memory bandwidth.

Of course, this story is incomplete without context. Back in 2017, NVIDIA refreshed the GTX 1060 6 GB with 9 Gbps GDDR5 memory (216 GB/s). That variant, although available in some places, isn't the predominant GTX 1060 6 GB variant, as NVIDIA did not retire the original 8 Gbps GTX 1060 6 GB with its launch. This new GDDR5X variant comes with even lower memory clock and bandwidth than that 9 Gbps refresh. The card still only has 1,280 CUDA cores, and the GPU is factory-overclocked by Palit at 1531 MHz core, and 1746 MHz GPU Boost. At best, GDDR5X could vastly improve overclocking headroom, since NVIDIA's partners could be using 10 Gbps-rated GDDR5X chips, which are known to overclock well beyond 11 Gbps.

AMD is giving final touches to its Radeon RX 590 graphics card, which is rumored to be based on an efficient new rendition of the "Polaris" silicon, which could disturb NVIDIA's product lineup between the GTX 1060 series and the GTX 1070, as its new RTX 2060 series is nowhere in sight. In a bid to thwart this threat, NVIDIA is preparing a variant of the GeForce GTX 1060 with faster GDDR5X memory.

The current GTX 1060 6 GB is endowed with 8 Gbps GDDR5 memory, which at its 192-bit bus width works out to a memory bandwidth of 192 GB/s. NVIDIA had attempted to improve its competitive position once, by creating a shortlived sub-variant of this SKU with 9 Gbps GDDR5 memory (211 GB/s). Switching to 10 Gbps GDDR5X memory would give the chip 240 GB/s memory bandwidth, and 11 Gbps (unlikely because expensive), would yield 264 GB/s. With the GP106 silicon maxed out, it's also possible the new GTX 1060 could be based on a heavily cut down GP104, possibly even with 192-bit memory, which explains GDDR5X memory.

NVIDIA's upcoming GeForce GTX graphics cards based on the "Volta" architecture, could feature GDDR6 memory, according to a supply deal SK Hynix struck with NVIDIA, resulting in the Korean memory manufacturer's stock price surging by 6 percent. It's not known if GDDR6 will be deployed on all SKUs, or if like GDDR5X, it will be exclusive to a handful high-end SKUs. The latest version of SK Hynix memory catalogue points to an 8 Gb (1 GB) GDDR6 memory chip supporting speeds of up to 14 Gbps at 1.35V, and up to 12 Gbps at 1.25V.

Considering NVIDIA already got GDDR5X to run at 11 Gbps, it could choose the faster option. Memory remains a cause for concern. If 8 Gb is the densest chip from SK Hynix, then the fabled "GV104" (GP104-successor), which could likely feature a 256-bit wide memory interface, will only feature up to 8 GB of memory, precluding the unlikely (and costly) option of piggy-backing chips to achieve 16 GB.

EVGA today introduced two new color variants of its GeForce GTX 1080 Ti SC2 Elite Gaming graphics card. These include the Green (model: 11G-P4-6693-K4), and blue (11G-P4-6693-K3). EVGA colored the aluminium frame-type cooler shroud with anodized blue or green paint. That's all there is to these variants, which are priced on par with the regular model that has a silver shroud color. The factory-overclocked cards ship with clock speeds of 1556 MHz base, 1670 MHz GPU Boost, and an untouched 11 GHz (GDDR5X-effective) memory. Both new variants are priced the same, at USD $949.99, on EVGA web-store.

ELSA 's appearances in TechPowerUp's front pages have been few and far between, with the last iteration of a graphics card from this manufacturer having made its way into our news feed around February 5th, 2015, with its GTX 960 SAC graphics card. That doesn't mean they ELSA isn't worthy of our attention, though, so here goes: the announcement of a GeForce GTX 1080 Ti graphics card.

The ELSA GeForce GTX 1080 Ti 11 GB ST graphics card features a stock blower design that's reminiscent of those offered in AMD's base models, with a subdued black and silver color scheme. It's a pretty graphics card, though it will likely be let down by its cooling and acoustic performance. Specs are vanilla when it comes to NVIDIA's reference GTX 1080 Ti clocks: there's a base clock of 1,480 MHz (actually 1 MHz lower than NVIDIA's reference) and 1,582 MHz Boost, with 11 GB of 11 GHz GDDR5X memory. The ELSA GTX 1080 Ti 11GB ST graphics card draws power from the PCIe bus, and from 1x 6-pin and 1x 8-pin connectors. Display outputs on this dual-slot graphics card come in at 3x DisplayPort, 1x Dual link DVI-D, and 1x HDMI 2.0b. The card's dimensions stand at 266 mm (L) x 111 mm (H) x 39 mm (D).

GIGABYTE today rolled out the GV-NP104D5X-4G, a mining graphics card based on NVIDIA P104-100 mining processor. Derived from the "GP104" silicon, the P104-100 is configured with 1,920 CUDA cores on this card, paired with 4 GB of GDDR5X memory across its 256-bit wide memory interface. What's more interesting, although the GP104 features a PCI-Express 3.0 x16 bus interface, the card has only x4 wiring, although the slot interface itself is of x16 length.

The GPU core clock speed for the GV-NP104D5X-4G is 1607 MHz, with 1733 MHz GPU Boost, and its memory is clocked at 10 GHz (GDDR5X-effective). The card draws power from a single 8-pin PCIe power connector, and has no display outputs. It's cooled by a rather simple aluminium fin-stack heatsink, ventilated by three fans, carried over from the company's latest WindForce 3X cooling solution. Unlike its consumer GeForce graphics cards, this card is backed by only a 3-month warranty. The card will be significantly cheaper than the GTX 1080 or GTX 1070.

EVGA today introduced its flagship graphics card, the GeForce GTX 1080 Ti K|ngp|n Hydro Copper (model: 11G-P4-6799), tuned by the legendary overclocker Vince "K|ngp|n" Lucido himself. The card features the choicest VRM components, binned "GP102" ASIC and GDDR5X memory chips, to support not just the highest overclocking headroom among EVGA's lineup, but also its highest factory-overclocked speeds of 1582 MHz core, 1695 MHz GPU Boost, and 11.00 GHz (GDDR5X-effective) memory clocks.

The card is intended to be plumbed to your own liquid-cooling loop, and comes with an all-copper, full-coverage water-block. You also get EVGA's iCX technology, which puts 9 thermal sensors across various points in the card. Available now (in limited stocks), exclusively through EVGA's own online store, the card is priced at USD $1,249.

NVIDIA has been doing a great job maintaining its leadership position in the discrete, high-performance graphics segment with its Pascal graphics cards. Rival AMD delivered a somewhat unconvincing effort with its RX Vega graphics cards - to which NVIDIA has already answered the most interesting AMD graphics card in that lineup, the Vega 56, with its own GTX 1070 Ti. As such, corporate bottom lines and profit maximization likely mean that the company is in no rush to introduce its Volta architecture to the gaming market. However, the company's recent tease either marks the first iteration of a halo product based on the company's Volta architecture to the market, or, more likely, a limited edition Titan X graphics card still based on the Pascal architecture - as if the Titan Xp wasn't limited and premium enough, naturally, but I digress.

The short teaser, posted by NVIDIA on its GeForce Facebook page under the "It's coming...a Collector's Edition" tagline, shows a distinguished-looking cooler shroud, which borrows design elements from the company's iconic Founders Edition graphics card, but with some added geometry and detail touches. The card will apparently incorporate RGB elements, seeing as the teaser shows both green and red colors. There's some speculation that this Collector's Edition Titan graphics card could be the first consumer graphics card to leverage GDDR6 memory, upping the ante from today's top of the technological crop, GDDR5X. Time - NVIDIA - will tell.

ASUS rolled out a special variant of its Republic of Gamers (ROG) Strix GeForce GTX 1080 Ti graphics card commemorating "Assassin's Creed: Origins." The card features a special cooler shroud with bronze-gold die-cast color forming the top half, and a groovy hieroglyph print with ROG and Assassin's Creed logos, on the back-plate, again in bronze-gold. The SKU includes a coupon to the standard edition of "Assassin's Creed: Origins," redeemable on UPlay.

The card is otherwise identical to the ROG Strix GTX 1080 Ti OC, including its out of the box clock speeds of 1569/1683 MHz (core/boost), and an untouched 11 GHz (GDDR5X-effective) memory. It also retains the RGB LED lighting along inserts on the cooler shroud, and the ROG logo on the back-plate. This card could be priced at a slight premium over the ROG Strix GTX 1080 Ti OC.

GIGABYTE today rolled out the Aorus GTX 1080 Gaming Box, an external graphics solution built on the same platform as the company's GTX 1070 Gaming Box, but taking advantage of its new GeForce GTX 1080 Mini graphics card, which is the world's most compact card based on this chip. The enclosure powers the card with an 80 Plus Gold-certified 450W PSU. It connects to the host machine using 40 Gbps Thunderbolt 3, and puts out downstream connectivity that includes four 5 Gbps USB 3.0 ports, from which one is a quick-charge port.

Under the hood, the GeForce GTX 1080 graphics card ticks at reference clocks out of the box, but has a software-enabled "OC Mode" which spools them up to 1632/1771 MHz (core/boost). The memory is clocked at 10 GHz (GDDR5X-effective). Display outputs include three DisplayPort 1.4 and one each of HDMI 2.0 and dual-link DVI-D. The enclosure is studded with RGB multi-color LEDs, which you control using the included GIGABYTE RGB Fusion software. The enclosure is expected to be priced around USD $750.

The EVGA GeForce GTX 1080 Ti FTW3 ELITE cards are now available with 12 GHz of GDDR5X memory, giving it 528 GB/s of memory bandwidth! These cards are available with either the ELITE Black or White shroud, and of course comes with EVGA's exclusive iCX technology, giving you 9 thermal sensors, onboard thermal LED indicators and incredible cooling with quiet operation.

Features

• Includes EVGA iCX Technology
• 12 GHz GDDR5X Memory
• 528 GB/s of Memory Bandwidth
• Available in ELITE Black and White Colors

NVIDIA is readying a new GeForce GTX 1070 refresh graphics card, according to well-placed sources. Positioned between the current GTX 1070 and the GTX 1080 11 Gbps in performance, the refreshed GTX 1070 could at least displace the current GTX 1070 from its price-point, if not replace it. NVIDIA could carve the new chip out of the latest stepping of the GP104 silicon, and give it more CUDA cores, likely 2,048 (on par with GTX 1070 Mobile), if not higher. It could also get faster memory, likely 9 Gbps GDDR5 or even 10 Gbps GDDR5X. Its core and GPU Boost clock speeds could even be dialed up a little.

NVIDIA's objective here appears to be convincingly outperforming AMD Radeon RX Vega 56, at a lower power-draw. There's a 20 percent performance gap between the current desktop GTX 1070 and GTX 1080, and the new GTX 1070 refresh could find a price-performance equation somewhere in the middle. As NVIDIA's product-stack currently stands, the GTX 1080, which was refreshed with faster 11 Gbps GDDR5X memory, has a wider performance gap with the GTX 1070, creating room for a GTX 1070 refresh SKU somewhere in the middle, which could perform within the 90th percentile of the original GTX 1080 with 10 Gbps memory. What NVIDIA could name the SKU is anybody's guess. Historically, NVIDIA has updated SKU specifications without changing the name. The GTX 1080 and GTX 1060 6 GB were refreshed with faster memory, by simply prominently mentioning the memory clock below the SKU branding, there's also the remote possibility of the GTX 1070 Ti branding to combat the "grandeur" of AMD's RX Vega branding. NVIDIA could have the new GeForce GTX 1070 refresh SKU out in time for Holiday.

GIGABYTE rolled out what it claims to be the shortest GeForce GTX 1080 graphics card, the GV-N1080IX-8GD. With a length of just 169 mm, the card is significantly shorter than the 211 mm length of ZOTAC GTX 1080 Mini, the previous record-holder for the smallest GTX 1080 graphics card. The card features a dense aluminium fin-stack heatsink to which heat drawn directly from the GPU is conveyed by copper heat pipes; and ventilated by a single 90 mm fan, which remains off when the card is idling.

Out of the box, the GIGABYTE GTX 1080 Mini comes with NVIDIA-reference clock speeds of 1607 MHz core, 1733 MHz GPU Boost, and 10.00 GHz (GDDR5X-effective) memory, but a software-enabled OC mode spools up GPU clocks to 1632/1771 MHz. The card draws power from a single 8-pin PCIe power connector, and conditions it using a 5+2 phase VRM. Based on the 16 nm "GP104" silicon, the GeForce GTX 1080 features 2,560 CUDA cores, 160 TMUs, 64 ROPs, and a 256-bit wide GDDR5X memory interface, holding 8 GB of memory. Display outputs include three DisplayPort 1.4, and one each of dual-link DVI and HDMI 2.0. The company didn't reveal pricing.

It has been a while since the launch of NVIDIA's GTX 1080 (manli had even come out of the gate with a Founders Edition version of this SKU), but the company has now added another option to its lineup. The M-NGTX1080/5RGHDPPP-BL doesn't do much to differentiate itself from what's already in the market, though.

The new Manli card sports a blower-style cooler, reference GTX 1080 specs, a core base clock of 1607MHz, a core boost clock of 1733MHz and 8GB of GDDR5X memory (10 GHz). Connectivity-wise, we're treated to 1x dual-link DVI-D, 1x HDMI 2.0b and 3x DisplayPort 1.4 output ports. The card is backed by a two year warranty, and should hit retail for $595.

In a bid to preempt sales of the Radeon Pro Vega Frontier Edition, and the Pro WX 9100, NVIDIA expanded the feature-set of its consumer-segment TITAN Xp graphics card, with certain features reserved for its Quadro family of graphics cards, through a driver update. NVIDIA is rolling out its latest GeForce software update, which adds professional features for applications such as Maya, unlocking "3X more performance" for the software.

Priced at USD $1,199, the TITAN Xp packs a full-featured "GP102" graphics processor, with 3,840 CUDA cores, 240 TMUs, 96 ROPs, and 12 GB of GDDR5X memory across the chip's 384-bit wide memory interface. At its given memory clock of 11.4 GHz (GDDR5X-effective), the card has a memory bandwidth of 547.6 GB/s, which is higher than the 484 GB/s of the Radeon Pro Vega Frontier Edition.DOWNLOAD: NVIDIA GeForce 385.12 for TITAN Xp

Colorful Technology Company Limited, professional manufacturer of graphics cards and motherboards, produces its flagship graphics card iGame GTX 1080 Ti Kudan in China which takes the most advanced technology into performances. Using "Jiu Duan" as name, iGame has produced one advanced flagship card each year and each GP102 chip of "Jiu Duan" has been selected from 100 chips because of its high one key overclocking frequency setting before factory.

From the first generation iGame GTX 560 Ti "Jiu Duan", this has been the 7th year to produce but 8th generation "Jiu Duan". Pursuing extreme performance, iGame officially debuts the international name for the whole series GPUs, then the 8th generation "Jiu Duan" is changed to "Kudan" , that is iGame GTX 1080 Ti Kudan.

Colorful Technology Company Limited, professional manufacturer of graphics cards and motherboards, officially debuts the international name for its liquid-cooled GPUs with the announcement of the Neptune series of graphics cards, starting off with the most powerful model which debuted in COMPUTEX, the iGame GTX 1080 Ti Neptune W.

The iGame GTX 1080 Ti Neptune W ships with 3584 CUDA cores, and runs at a base clock frequency of 1594 MHz while the GPU Boost clock speed can go up to 1708 MHz. To improve the performance even further, the iGame GTX 1080 Ti Neptune W has also been outfitted with GDDR5X memory module running at 11 Gbps that bring gamers more powerful game performance.

EVGA's product manager Jacob Freeman has just confirmed the launch day of EVGA's upcoming end-all-be-all GTX 1080 Ti Hybrid FTW3 video card: it's now a relatively set in stone July 10th. Expect immediate availability for the video card on that day, though for now, not even Freeman has an idea if it will be available for ordering outside of EVGA's own online website.

The GTX 1080 Ti Hybrid FTW3 makes use of a hybrid, air and water-cooling solution. The GPU die itself is cooled by an Asetek all-in-one closed-loop liquid cooler, while memory and VRM make do with a traditional heatsink and fan combination. This provides the benefit of liquid cooling on the GPU core without the added expense of a full-cover waterblock, thus bringing the pricing a little lower than full-coverage waterblocks, but with increased performance over a purely air-cooled part. The GTX 1080 Ti HYBRID FTW3 shares the same specs as the 1080 Ti SC2 HYBRID, Hydro Copper, and Hydro Copper SC2 graphics cards, with a 1,556 MHz base and 1,670 MHz boost clock, 11 Gbps GDDR5X memory and 2x 8-pin power connectors. Pricing or overclocking headroom weren't detailed at all.

GIGABYTE, which had two variants of its flagship GeForce GTX 1080 Ti graphics card, the air-cooled Aorus GTX 1080 Ti Xtreme Edition, and the WaterForce WB Xtreme Edition, that comes with a factory-fitted full-coverage water-block; introduced a third variant, the WaterForce Xtreme Edition. Unlike the WaterForce WB Xtreme Edition, which you plumb to your own water-cooling loop, this card comes with a self-contained AIO liquid-cooling loop. The cooling solution consists of an pump-block base which makes contact with the GPU and a base-plate that draws heat from the VRM and memory; and a 120 mm radiator with an included 120 mm fan. The cooler-shroud features some groovy acrylic windows, and RGB LED lighting controlled by GIGABYTE RGB Fusion software.

The card is based on the same exact PCB as its two other siblings, with the same clock speeds of 1607 MHz core, 1721 MHz GPU Boost, and 11.2 GHz (GDDR5X-effective) memory out of the box, against NVIDIA-reference clocks of 1480 MHz core, 1582 MHz GPU Boost, and 11.00 GHz memory. The software-enabled "OC mode" runs the card at 1632 MHz core, 1746 MHz GPU Boost, and 11.44 GHz memory. The card draws power from a pair of 8-pin PCIe power connectors. Display outputs include three DisplayPort 1.4, three HDMI ports (two on the rear panel, one internal HDMI port for VR headsets); and a dual-link DVI connector. The company didn't reveal pricing.

GIGABYTE launched a variant of its flagship Aorus GeForce GTX 1080 Ti Xtreme Edition graphics card, which is prepped for water-cooling. The new Aorus GTX 1080 Ti Waterforce WB Xtreme Edition comes with a factory-fitted full-coverage water-block, which you plumb to your water-cooling loop. The block is made of nickel-plated copper, with a clear acrylic top, and an aluminium+plastic top-plate with a cutout the shape of the Aorus logo. The acrylic top is studded with RGB multi-color LEDs, which can be controlled using GIGABYTE RGB Fusion software.

The Aorus GeForce GTX 1080 Ti Waterforce WB Xtreme Edition comes with out of the box clock speeds of 1607 MHz core, 1721 MHz GPU Boost, with a software-enabled "OC mode" which cranks up clocks to 1632/1746 MHz; compared to NVIDIA-reference clocks of 1480/1582 MHz. The memory is left untouched at 11 GHz (GDDR5X-effective). The card draws power from a pair of 8-pin PCIe power connectors; and features a similar, VR-optimized display connector layout to its air-cooled sibling, which includes three DisplayPort 1.4, two HDMI 2.0, and one dual-link DVI-D where you'd expect them, plus a third HDMI connector near the card's tail end (facing the front of your case). The company didn't reveal pricing.