PowerColor on Wednesday formally launched its flagship graphics card, the Radeon RX 7900 XTX Liquid Devil. Designed for enthusiasts with DIY liquid-cooling setups, the Liquid Devil is essentially an RX 7900 XTX Red Devil, but with a factory-fitted full-coverage water block instead of the massive air cooler. The block has been made by EK Water Blocks, and consists of a nickel-plated copper main material, with a clear-acrylic top, and some vinyl decals. The top is studded with ARGB LEDs. The block lacks fittings, but has G 1/4" threading, and PowerColor has included goodies such as an EK-Loop Leak Tester Flex kit (lets you check for coolant leaks).

The PowerColor RX 7900 XTX has an ace up its sleeves that positions it above the Red Devil OC—the "Unleash" BIOS. The card has a dual-BIOS setup, with the default BIOS being labeled "OC" and the other one being "Unleash." OC enables speeds comparable to the Red Devil OC—2395 MHz game and 2565 MHz boost (vs. 2269 MHz game and 2499 MHz boost AMD reference speeds). PowerColor is yet to spell out the clock speeds of the "Unleash" BIOS, but we're hearing that it will be even higher (possibly the highest factory OC for the RX 7900 XTX), along with increased power-limits. The PowerColor RX 7900 XTX Liquid Devil should be available from mid-February, 2023.

The Windows app of Discord, the popular social-networking software, apparently trims the graphics card memory clock of NVIDIA GPUs by an innocuous 200 MHz, or so observe gamers. NVIDIA GeForce GPUs dynamically adjust memory clock speeds in response to load, as part of their power-management. Ideally, with gaming workloads, the GPU is supposed to hit its maximum rated memory frequency, but some keen-eyed gamers with monitoring tools noticed that with the Discord app running in the background, the memory clock tops out at T-minus 200 MHz (i.e. if it was supposed to be 7000 MHz, it tops out at 6800 MHz). Even under the infernal stress of Furmark, something that's designed to push memory clocks to the maximum rated speeds until the graphics card runs into thermal limits; the memory clock is seen falling 200 MHz short.

NVIDIA took note of this issue, and assured that a fix is on the way in a future GeForce driver update. In the meantime, it posted a DIY workaround to the problem that involves downloading the GeForce 3D Profile Manager utility, making the utility "export SLI profiles" (applicable even to single-GPU machines), editing the exported SLI profiles file as a plaintext document, and importing the profile back. This basically alters the way the driver behaves with the Discord app running. The NVIDIA 3D Profile Manager utility can be downloaded from here, and step-by-step instructions on using it to fix this issue, here.Update Feb 6th: NVIDIA released a GeForce driver application profile that automatically downloads to your driver, which should fix this issue. You don't need GeForce Experience to receive the update.

GUNNIR, the Chinese Intel Arc board partner, unveiled a 16 GB version of its Arc A770 Photon graphics card with specs that partially match Intel's A770 16 GB Limited Edition. Custom-design versions of the A770, such as the one from ASRock Phantom Gaming, only come with 8 GB of memory. The card comes with GUNNIR's heaviest dual-slot, triple-fan cooling solution. While the card offers an overclocked GPU, with the A770 running at 2.40 GHz (compared to 2.10 GHz reference), the memory runs at the same 16 Gbps GDDR6-effective speed as the A770 8 GB version, and not the 17.5 Gbps that the A770 16 GB Limited Edition comes with. This leaves you with a still-respectable 512 GB/s of memory bandwidth on tap. The card draws power from two 8-pin PCIe power connectors. GUNNIR is pricing the card at RMB ¥3,199 ($470).

GIGABYTE displayed their latest motherboards and graphics cards at the 2023 International CES, covering their Socket LGA1700 Intel 700-series chipset; and Socket AM5 AMD 600-series chipset. The Z790 AORUS Tachyon is the company's top-grade LGA1700 motherboard targeting the professional overclocking crowd. The board is designed to chase down CPU and memory overclocking world records, featuring the company's most powerful CPU VRM solution, and a 1 DIMM-per-channel DDR5 memory setup that preferred by overclockers for supporting the highest memory overclocks with the tightest timings. There are several overclocker-friendly features besides the onboard buttons—dual-BIOS ROMs, angled connectors for bench cases, consolidated voltage measurement points, and a feature-packed BIOS setup program.

Over in the AMD side, GIGABYTE's top Socket AM5 motherboard is the X670E AORUS Xtreme, which is a feature-packed motherboard with possibly the strongest CPU VRM solutions in the market for Ryzen 7000 processors, and with the best VRM cooling. In addition to the PCIe Gen 5 M.2 slot wired to the AM5 SoC, you get additional Gen 5 slots that subtract from the x16 PEG slot. The AORUS Xtreme also has the most feature-rich BIOS available among GIGABYTE's AM5 lineup. The B650I AORUS Ultra is a premium Mini-ITX Socket AM5 motherboard based on the AMD B650 chipset. Despite its compact size, it gives you a PCI-Express 4.0 x16 PEG slot, a Gen 5 M.2 slot, and two additional Gen 4 M.2 slots, besides the latest wired- and wireless connectivity. We also snapped the B650 AERO G motherboard targeting creators, and the mainstream B650 AORUS Elite AX.

ASUS showed us its GeForce RTX 4080 Noctua Edition graphics card that it formally announced yesterday. To call this card thick would be an understatement, as it's possibly the first graphics card that is 5 slots thick! The card easily overshoots what constitutes 4 slots, and is technically 4.2 to 4.3 slots; but then expansion slot counts are whole numbers rounded to the next digit despite what marketing says.

This card combines an ASUS ROG Strix RTX 4080 PCB with an air-based cooling solution designed by Noctua. The cooler has two large aluminium fin-stacks that have been skewered by eight 6 mm-thick nickel-plated copper heatpipes, and ventilated by a pair of Noctua's top-of-the-line NF-A12x25 120 mm fans that feature fluid-dynamic bearings. The fan-tuning for this card is a Noctua-ASUS collaboration, and promises to make this the quietest air-cooled RTX 4080 you can buy.

ASUS today announced the GeForce RTX 4080 Noctua Edition graphics card, a continuation of its collaboration with the legendary cooling company, building on the previous GeForce RTX 3070 and RTX 3080 Noctua variants. This year ASUS and Noctua have worked together to tame the power of the mighty GeForce RTX 4080 graphics card. Noctua fan-design prowess and an ASUS custom-built vapor chamber combine to create the quietest air-cooled RTX 4080 on the market.

Cool and quiet
The ASUS GeForce RTX 4080 Noctua Edition incorporates a pair of state-of-the-art Noctua NF-A12x25 fans to move air over a massive heatsink, developed in a partnership between the veteran ASUS thermal R&D team and the engineers at Noctua. The engineers successfully refined the fin density and heat pipe arrangement of the heatsink, optimizing it for the airflow characteristics of the NF-A12x25. To prioritize low noise levels, a smooth acoustic signature and high cooling performance while making room for the pair of 120 mm fans, ASUS expanded the card's total volume to occupy 4.3 slots of space. The card features a Dual BIOS switch, and Quiet mode is enabled by default to minimize noise right out of the box.

Colorful Technology Company Limited, a world-renowned manufacturer of desktop components, laptops, desktops, AIO PCs, and storage, launches its lineup of GeForce RTX 4070 Ti graphics cards featuring the Vulcan, Neptune, Advanced OC, Ultra White, and NB Series models. All the new COLORFUL GeForce RTX 4070 Ti Series graphics cards uses PCIe 5.0 16-pin 12VHPWR connectors.

The COLORFUL RTX 4070 Ti Series adopts the new look and designs as seen on the RTX 4090 and RTX 4080 Vulcan, Neptune, Advanced, Ultra White, and NB Series models but in slimmer form-factor. The COLORFUL GeForce RTX 4070 Ti Series comes in air-cooled and liquid-cooled models that will meet the needs of enthusiasts and gamers.

SAPPHIRE Technology also launches the SAPPHIRE PULSE AMD Radeon RX 7900 Series Graphics Cards for great gaming performance at excellent value. The PULSE AMD Radeon RX 7900 XTX Graphics Card headlines with 96 Compute units and 6144 stream processors running with a Boost Clock of up to 2525 MHz and a Game Clock of up to 2330 MHz. The PULSE AMD Radeon RX 7900 XT features 84 Compute Units with 5376 stream processors, a Boost Clock of up to 2450 MHz and a Game Clock of up to 2075 MHz. Visualize the latest 24 GB and 20 GB respectively of GDDR6 high-speed memory clocked at 20 Gbps Effective with 96 MB and 80 MB respectively of Infinity Cache. The graphics card supports up to 4 output ports including 2x HDMI 2.1 and 2x DisplayPort 2.1 ports with DSC outputs to align with the latest monitors on the market.

The SAPPHIRE PULSE AMD Radeon RX 7900 Series Graphics Cards run on SAPPHIRE's distinguished Tri-X Cooling Technology which work in tandem with the Intelligent Fan Control and Precision Fan Control features to keep temperatures low and fan noise low. Stability and reliability are key pillars of the PULSE AMD Radeon RX 7900 Series Graphics Cards. The High TG Copper PCB design enables stable and reliable performance resulting in a low temperature and low noise PCB component. The crucial Fuse Protection feature is built into the circuit of the external PCIe power connector to keep the components safe. As part of SAPPHIRE's motto of long-lasting components, Dual-Ball Bearing Fans are fitted to increase the lifespan of the Graphics Cards.

SAPPHIRE Technology announces the heavily anticipated NITRO+ AMD Radeon RX 7900 Vapor-X Series Graphics Cards, with breakthrough performance and incredible clock speeds for both gamers and creators 4K and beyond. The cards are crafted with SAPPHIRE's signature cutting-edge cooling features, quality of life components and engineered to push high framerates with the optimal balance of heat and noise.

At the core of the NITRO+ Graphics Cards series are the technologies of the SAPPHIRE PANTHEON Suite of permanent features. SAPPHIRE PANTHEON guarantees supreme cooling technology and other distinct features exclusive to NITRO+ graphics cards. Each NITRO+ iconic feature stands as strong and permanent as the pillars of the PANTHEON. Every NITRO+ Graphics Card guarantees the presence of the stable, reliable and innovative SAPPHIRE PANTHEON suite of features.

BIOSTAR, a leading manufacturer of motherboards, graphics cards, and storage devices today, is excited to unveil two brand-new Radeon RX 7900 series graphics cards. Powered by the groundbreaking AMD RDNA 3 architecture, BIOSTAR is latest Radeon RX 7900XTX-24GB and RX 7900XT-20GB graphics cards deliver up to 50% more performance per watt than their previous generation RDNA 2 GPU units. Featuring AMD is superior RDNA 3 architecture and the world is fastest interconnect technology, the all-new BIOSTAR Radeon RX 7900XTX and RX 7900XT graphics cards combine 5 nm and 6 nm process nodes with updated chiplets that leverage AMD is Infinity Links and high-performance fanout packaging to deliver blazingly fast 5.3 TB/s bandwidth.

Unleash jaw-droppingly high frame-rates on AAA game titles with breathtaking 4K visuals powered by AMD is most advanced graphics technology with BIOSTAR is Radeon RX 7900XTX and RX 7900XT graphics cards. Ideal for gamers and content creators, they carry AMD is second-generation Infinity Cache technology and high-speed GDDR6 memory with up to a 384-bit memory interface.

GIGABYTE TECHNOLOGY Co. Ltd, a leading manufacturer of premium gaming hardware, today announced the new AMD Radeon RX 7900 Series graphics cards powered by the high-performance, energy-efficient AMD RDNA 3 architecture - the AORUS Radeon RX 7900 XTX ELITE 24G, Radeon RX 7900 XTX GAMING OC 24G, Radeon RX 7900 XTX 24G, Radeon RX 7900 XT GAMING OC 20G and Radeon RX 7900 XT 20G graphics cards. The new graphics cards will be available for purchase on December 13, 2022.

The new graphics cards are the world's first gaming graphics cards to feature an advanced AMD chiplet design, delivering exceptional performance and superb energy efficiency to power high-framerate 4K and higher resolution gaming in the most demanding titles.

ASRock, the leading global motherboard, graphics card and mini PC manufacturer, today launched the new AQUA, Taichi and Phantom Gaming series graphics cards based on AMD Radeon RX 7900 Series GPUs.

The new graphics cards are built on the groundbreaking AMD RDNA 3 architecture with chiplet technology. AMD RDNA 3 architecture delivers up to 54% more performance per watt than AMD RDNA 2, features the world's fastest interconnect linking the graphics and memory system chiplets at up to 5.3 TB/s, and offers up to 96 new unified compute units and second-generation AMD Infinity Cache technology. It also delivers increased AI throughput that provides up to 2.7X higher AI performance, and rearchitected compute units with second-generation ray tracing technology that provides up to 1.8X higher ray tracing architectural performance in select titles versus AMD RDNA 2 architecture.

Here's the first picture of the ASRock Radeon RX 7900 XTX AQUA, marking the debut of the company's top-of-the-line AQUA brand to its graphics card lineup. The ASRock AQUA line of motherboards come with liquid monoblocks that let you cool the processor, chipset, and CPU VRM using your own DIY liquid-cooling loop. The Radeon RX 7900 XTX comes with a factory-fitted full-coverage water block. The OEM of this block is unknown (could be either CoolIT or Bitspower). The block features a nickel-plated copper primary material, with an acrylic top and vinyl film for the brushed-aluminium look. The top is studded with addressable RGB LEDs. The block sits on top of ASRock's most premium custom-design PCB for the RX 7900 XTX, which pulls power from three 8-pin PCIe power connectors.

With 11 days to go until the official launch of AMD's Radeon 7900-series graphics cards, PowerColor decided to share some more details about its upcoming cards. The two models appear to be the Hellhound Radeon RX 7900 XTX and the Hellhound Radeon RX 7900 XT, with both cards apparently sharing the same design and cooler. The cards appear to be at least triple-slot, but it's not entirely clear from the provided pictures. PowerColor is using a nine-blade fan design and the fans are of course kitted out with LEDs, where PowerColor is pushing what it calls an "amethyst purple" colour for this generation of Hellhound cards. The new fans are said to improve the GPU temperatures by as much as three degrees Celsius compared to the previous generation of fans.

More importantly, the cards have been given an improved backplate, as well as a larger copper plate for the heatsink, for improved cooling. The new copper plate doesn't just cover the GPU now, but also the VRAM chips. The copper plate is connected to eight 6 mm heatpipes. PowerColor also shared that it's using a 14-layer high TG PCB, which uses a two ounce copper power layer. The RX 7900 XTX is kitted out with 20 VRMs, although this appears to be straight from the AMD reference design. PowerColor appears to have implemented a dual BIOS on the card, as there's a switch for OC/Silent operation and the card also appears to have a hardware LED switch, which is nice for those that don't care about lighting up their computer like a Christmas tree. Keep in mind that this is not PowerColor's top-of-the-range card, which is the Red Devil, so we should expect more details on those cards in the future too.

NVIDIA is ready to launch its RTX A6000 series "Ada" professional-visualization graphics cards. These cards are targeted at the same market demographic as the NVIDIA Quadro series of the old—serious 3D content creation. The RTX A6000 leads the pack, and is based on the 4 nm "AD102" silicon (the same one powering the GeForce RTX 4090). The A6000 is better endowed than the RTX 4090 at the silicon-level, although operating at lower GPU clock-speeds, for its tighter 300 W power-limit (compared to 450 W of the RTX 4090).

The A6000 "Ada" is endowed with 18,176 CUDA cores across 142 SM, compared to the 16,384 CUDA cores across 128 SM of the RTX 4090. It also gets a higher number of Tensor cores, at 568. The defining differentiator between the A6000 and RTX 4090 has to be memory, with the pro-vis card getting 48 GB of ECC GDDR6 memory across the chip's 384-bit memory bus, clocked at 20 Gbps (960 GB/s memory bandwidth); compared to the 24 GB of 21 Gbps GDDR6X (1008 GB/s) of the RTX 4090. Also, the card enables all three NVDEC and NVENC video hardware-accelerators physically present on the AD102, for six independent accelerated transcoding streams.

Colorful formally released its flagship custom-design graphics card based on the GeForce RTX 4080 "Ada" launched earlier this week, the iGame RTX 4080 Neptune OC-V. This card features a factory-fitted all-in-one (AIO) liquid cooling solution. Unlike some other similar cards, such as the MSI SUPRIM Liquid X, the Neptune OC-V relies on a 100% liquid-cooled configuration, wherein a the cold-plate is the only source of cooling for the GPU, memory, and VRM; there are no additional fans on the card. The cooling solution involves a waterblock that pulls heat from all key components on the PCB, which is connected to a 360 mm x 120 mm radiator that comes with three 120 mm RGB fans.

The card is 25.3 cm in length, strictly 2 slots thick, and 17 cm in height. Silvery aluminium makes up the cooler shroud and backplate. The coolant tubing comes with white Nylon sleeving. The aluminium radiator has a white frame, as do the three fans. The fan impellers are frosted to act like RGB diffusers. The Neptune OC-V comes with factory-overclocked speeds of 2640 MHz GPU Boost (compared to 2505 MHz reference). The most interesting aspect is the power limit, which is now set at 470 W (compared to 320 W reference).

The world's leading computer brand, GIGABYTE, today officially announced the GeForce RTX 4080 series graphics cards will hit the market on November 16th. Built on NVIDIA's latest Ada Lovelace architecture, these new-gen graphics cards come with ultra-powerful performance and advanced cooling solutions that enthusiast gamers and creators seek. GIGABYTE offers a total of seven models to meet various demands, including the liquid-cooled AORUS XTREME WATERFORCE and the air-cooled AORUS MASTER, GAMING OC, AERO OC, and EAGLE OC.

Primed for extremely cool and quiet operations, the AORUS XTREME WATERFORCE graphics cards come in two variants - the open-loop model with a pre-installed water block and the closed-loop model featuring an all-in-one cooler. Both excel in delivering the ultimate gaming performance while keeping the temperature well in check with their optimized water channel and thermal designs, making them ideal for hardcore gamers or PC DIY enthusiasts looking to take their custom builds to the next level.

ARCTIC, leading manufacturer of silent PC coolers and components, today informs about the new INNO3D GEFORCE RTX 4090 ICHILL BLACK graphics card. We love innovative projects and enthusiastically took on the challenge of taming NVIDIA's power-hungry new release. Working closely with INNO3D, we created an efficient liquid cooling system for graphics cards. With technical know-how, in cooling combined with a clean, uncluttered design and straight lines and edges, the INNO3D GEFORCE RTX 4090 ICHILL BLACK graphics card is rightfully called "Brutal by Nature".

We would like to thank INNO3D for their very good collaboration. The new GeForce RTX 4090 iCHILL BLACK features a hybrid cooling solution that combines quiet airflow with powerful water cooling. We have been creating cooling solutions for computer hardware for over 20 years. Successful products such as the P-Series fans as well as the ARCTIC Liquid Freezer II have found enormous appeal in the hardware industry. We set out to combine the successful aspects of these products to create a high-performance GPU cooler.

After ASRock, MSI, and ASUS, GIGABYTE is coming around to launch its Intel Arc custom-design graphics cards. The company has at least 5 Arc 3-series desktop graphics card SKUs planned, according to a leaked regulatory filing with the Eurasian Economic Commission (EEC). The lineup includes four SKUs based on the A380, and one on the A310. The A380 SKUs include base and factory-overclocked variants under the WindForce and Gaming brands, while the sole A310 SKU is under the WindForce brand. An EEC filing entry doesn't necessarily mean all five of these SKUs are being launched, companies tend to file placeholders, to avoid fresh filings for each SKU.

Jon Peddie Research (JPR) has responded to the recent dramatic reports by Canalys, Gartner, and IDC showing a precipitous drop in Q3 2022 PC shipments. In addition, JPR is providing guidance on the impact to graphics chip and AIB shipments. Jon Peddie, president and founder of JPR, said, "Our advice to clients has been consistent since 2020: The pandemic boom was not a surge in demand brought about by real growth in the market. The PC market is now correcting itself after a period of extraordinary growth spurred on by spending from an overwhelming surge of users working from home."

Peddie continued, "People were forced to work at home in 2020 and 2021, and many needed equipment. As a result, PC sales surged. Those people have what they need, and some of them are going back to the office. They don't need new PCs, and won't for three to five years. So, we are back to the nominal growth of the PC market, which was, and will be again after two quarters' adjustment, tracking GNP growth."

With the Eiswolf 2 AiO and the ES cooling block from the Enterprise Solutions series, Alphacool presents two innovative solutions for cooling Nvidia's latest graphics card. In order to dissipate the enormous waste heat of this graphics card generation in the best way possible, numerous optimizations have been made to the water cooler compared to the previous models. The fin structure has been adapted and allows a very high water flow while increasing the cooling surface. The modified jet plate with improved inflow engine ensures optimum distribution of the water over the cooling fins. The fully chrome-plated copper base is resistant to acids, scratches and damage. Additionally, the chrome plating provides homogeneity and shine that cannot be achieved by nickel plating.

This improved cooler is now being used in Alphacool's Eiswolf All-in-One as well as Enterprise Solutions in the industrial sector. The expandable Eiswolf 2 still scores as an all-round carefree package and ensures that its user can easily take advantage of a performance-oriented GPU water cooling with digital aRGB illumination out-of-the-box. Also still included are the NexXxos ST30 360 mm radiator, the Rise Aurora 120 mm fans, the Eiswolf 2 pump top with integrated DC-LT 2 pump and the TPV hoses with quick-release coupling. The ES cooler impresses with its technical design. The positioning of the connections at the rear allows easy integration of the GPU cooler into the water loop even in the tightest server cases. The discreet material mix of carbon and chrome-plated copper makes it additionally interesting for private users who can do without aRGB lighting.

ASRock today launched its Arc "Alchemist" A770 and A750 custom-design graphics cards. These include the A770 Phantom Gaming OC, and the A750 Challenger OC. The A770 maxes out the 6 nm ACM-G10 silicon, featuring all 32 Xe Cores (4,096 unified shaders); besides 16 Gbps GDDR6 memory; whereas the A750 gets 28 Xe Cores (3,584 unified shaders), and 16 Gbps GDDR6 memory. Both of ASRock's cards come with 8 GB of memory across a 256-bit wide memory bus, there's no 16 GB version of the A770 Phantom Gaming.

The ASRock A770 Phantom Gaming features a premium, RGB-illuminated cooling solution that's also found in the company's Radeon RX 6000-series Phantom Gaming graphics cards. This card also offers a factory-overclock of 2.20 GHz compared to 2.10 GHz reference. The cooler features a dual fin-stack heatsink with five 6 mm-thick nickel-plated copper heat-pipes that make indirect contact with the GPU over a copper base-plate. The dual ball-bearings fans come with idle fan-stop. There's a switch to manually turn off RGB lighting.

Intel announced the general availability of the Arc A770 and A750 performance-segment desktop graphics cards. This includes Intel's reference-design Limited Edition cards, and custom-design ones by the likes of ASRock, Gunnir, and Acer, among other OEMs. The A750 has a baseline price of USD $289, the A770 8 GB at $329, and the A770 16 GB at $349.

Based on the Xe-HPG "Alchemist" graphics architecture, the A750 and A770 are carved out of the same 6 nm ACM-G10 silicon. The A750 is configured with 28 Xe Cores, 448 EU, or 3,584 unified shaders; whereas the A770 maxes it out with 32 Xe Cores, 512 EU, or 4,096 unified shaders. Both cards get 256-bit wide GDDR6 memory interfaces, and while the A750 uses 16 Gbps memory (512 GB/s bandwidth); the A770 has 17.5 Gbps (560 GB/s).

Towards the latter half of August, multiple EVGA employees involved in technical marketing and engineering had let us know privately that they were leaving the company for other ventures. When pushed further, several hinted towards some decisions being made by EVGA's management, including CEO Andrew Han, that would jeopardize their future. Some even went far enough to say they would share more in a few weeks time about how they felt exactly about their time there, the various issues that kept them from doing their best, and also that at least a couple of ex-employees were let go. TechPowerUp was doing due diligence in collecting the facts while keeping emotions aside from contacts who were understandably not in the best of moods, and one thing common across the board was there was something major coming up dealing with the EVGA GPU product line.

Today EVGA decided to throw a massive curve ball by formally announcing the company is canceling its plans to carry the next generation of graphics cards. Given EVGA's revenue sheets point to nearly 80% contribution from being an NVIDIA add-in card partner, this effectively also means an end to a long partnership with NVIDIA. The company's CEO confirmed as much to a few media channels citing poor margins and a challenging, stressful relationship that was no longer fruitful. There are no plans for EVGA to partner with AMD or Intel at this time when it comes to graphics cards and the company stressed they will continue to sell and support current-gen GPUs having retained enough units for RMA purposes too.

During its GTC 2022 session, NVIDIA introduced its new generation of gaming graphics cards based on the novel Ada Lovelace architecture. Dubbed NVIDIA GeForce RTX 40 series, it brings various updates like more CUDA cores, a new DLSS 3 version, 4th generation Tensor cores, 3rd generation Ray Tracing cores, and much more, which you can read about here. However, today, we also got a new Ada Lovelace card intended for the data center. Called the L40, NVIDIA updated its previous Ampere-based A40 design. While the NVIDIA website provides sparse, the new L40 GPU uses 48 GB GDDR6 memory with ECC error correction. Using NVLink, you can get 96GBs of VRAM. Paired with an unknown SKU, we assume that it uses AD102 with adjusted frequencies to lower the TDP and allow for passive cooling.

NVIDIA is calling this their Omniverse GPU, as it is a part of the push to separate its GPUs used for graphics and AI/HPC models. The "L" model in the current product stack is used to accelerate graphics, with display ports installed on the GPU, while the "H" models (H100) are there to accelerate HPC/AI installments where visual elements are a secondary task. This is a further separation of the entire GPU market, where the HPC/AI SKUs get their own architecture, and GPUs for graphics processing are built on a new architecture as well. You can see the specifications provided by NVIDIA below.