NVIDIA and global manufacturers today announced powerful new NVIDIA RTX workstations designed for development and content creation in the age of generative AI and digitalization. The systems, including those from BOXX, Dell Technologies, HP and Lenovo, are based on NVIDIA RTX 6000 Ada Generation GPUs and incorporate NVIDIA AI Enterprise and NVIDIA Omniverse Enterprise software.

Separately, NVIDIA also released three new desktop workstation Ada Generation GPUs - the NVIDIA RTX 5000, RTX 4500 and RTX 4000 - to deliver the latest AI, graphics and real-time rendering technology to professionals worldwide. "Few workloads are as challenging as generative AI and digitalization applications, which require a full-stack approach to computing," said Bob Pette, vice president of professional visualization at NVIDIA. "Professionals can now tackle these on a desktop with the latest NVIDIA-powered RTX workstations, enabling them to build vast, digitalized worlds in the new age of generative AI."

Dell Technologies introduces new offerings to help customers quickly and securely build generative AI (GenAI) models on-premises to accelerate improved outcomes and drive new levels of intelligence. New Dell Generative AI Solutions, expanding upon our May's Project Helix announcement, span IT infrastructure, PCs and professional services to simplify the adoption of full-stack GenAI with large language models (LLM), meeting organizations wherever they are in their GenAI journey. These solutions help organizations, of all sizes and across industries, securely transform and deliver better outcomes.

"Generative AI represents an inflection point that is driving fundamental change in the pace of innovation while improving the customer experience and enabling new ways to work," Jeff Clarke, vice chairman and co-chief operating officer, Dell Technologies, said on a recent investor call. "Customers, big and small, are using their own data and business context to train, fine-tune and inference on Dell infrastructure solutions to incorporate advanced AI into their core business processes effectively and efficiently."

INNO3D, a leading manufacturer of pioneering high-end multimedia components and innovations proudly unveiled its much-awaited INNO3D GeForce RTX 4090 Frostbite new editions in Ultra and Pro. These next-generation INNO3D graphics cards promise unparalleled performance due to their Ada architecture. The iCHILL Frostbite has significant upgrades in both aesthetics and performance.

Dating back to 1998, INNO3D was founded with the aim to develop innovative computer hardware products on a global scale. Today, INNO3D is recognized in the gaming community for our avant-garde and bold approach to design and technology. We live by the mantra of being "Brutal by Nature" in all our endeavors, ensuring that we provide you with a superior gaming experience.

PC hardware enthusiast, harukaze5719, has stumbled upon a very understated looking custom GeForce RTX 4090 graphics card. MSI has produced a two-unit wide blower-type cooling system for the current flagship NVIDIA 40-series GPU, with Chinese PC hardware retailer—3DStor.com—being the only semi-official source of information. MSI's own web presences have not been updated to include their new GeForce RTX 4090 Aero S 24G model. The e-retailer does not provide any pricing information, but several examples (more than ten) are available to purchase via mujitech3's Ebay store. The Ningbo-based seller is charging a cool $3065 per card, plus an additional $80.00 for international shipping.

According to 3dstor's listing, the relatively compact custom design sticks to NVIDIA's recommended reference specifications (boost clock reaching 2520 MHz), but a 350 W TGP looks to be a bit iffy (coupled with the board's 16-pin 12VHPWR connector)—Tom's Hardware observed that this: "is 100 W lower when compared to regular RTX 4090 AIBs. We must assume that this is a typo and that its TGP is the same as other RTX 4090 graphics cards, which are currently the best graphics cards for gaming. Meanwhile, when the board peaks at 450 W, its blower-based cooling system likely gets extremely loud." The low-key monolithic shroud design suggests that MSI is likely targeting professional types with its Aero S 24G model, although gamers eyeing a compact build will be well catered to...if they can spare the expense.

EK, the leading computer cooling solutions provider, now offers EK-Pro GPU WB RTX 6000 Ada Rack - Nickel + Inox, an enterprise-grade full-cover water block meticulously designed for NVIDIA RTX 6000 Ada Generation graphics cards. Crafted to excel in rack mount environments, this cutting-edge water block leverages the power of the NVIDIA Ada Lovelace Architecture. Its exceptional construction showcases a CNC-machined nickel-plated copper base, complemented by a laser-cut stainless-steel top, creating a resilient liquid cooling solution that effectively transforms into a space-saving single-slot assembly. It encompasses the entire GPU, VRAM, and VRM components, precisely channeling the cooling liquid over these critical areas to efficiently dissipate heat.

The EK-Pro GPU WB RTX 6000 Ada Rack - Nickel + Inox is a purpose-built water block allowing you to have a professionally liquid-cooled NVIDIA RTX 6000 Ada Generation graphics card, perfectly suited for server rack installations. Designed to seamlessly integrate into standard Full Height Full Width (FHFW) server chassis form factors, these EK-Pro Rack GPU water blocks serve as convenient drop-in replacements for both active and passive dual-slot air coolers.

NVIDIA today launched the 16 GB version of the GeForce RTX 4060 Ti "Ada" graphics card to no fanfare. Essentially a memory variant of the RTX 4060 Ti with no other changes in the specs sheet, the RTX 4060 Ti 16 GB commands a $100 premium (25%) over the regular RTX 4060 Ti for double the memory size, albeit at the same 128-bit memory bus width, and the same 18 Gbps memory speed. The idea behind the card is that the larger memory should help in scenarios where the 8 GB of memory is found to limit performance. It would've been fun to test this theory if only we had cards to review—we didn't.NVIDIA's own presentation lists just two games that show gains, and that's probably the best-case.

If you've seen our coverage of the original RTX 4060 Ti or RTX 4060, you'll notice that we've tested 8 to 10 of each on launch day, covering almost every AIC partner. With the RTX 4060 Ti 16 GB, we were ready to repeat this feat, and cleared our calendars for the launch, except nothing came through. We talked to all the partners, and friends in the industry. We learned that neither NVIDIA nor the partners are sampling the RTX 4060 Ti 16 GB. We did try to arrange samples through back-channels, which turned out to be a bust, too, nobody wanted to touch these cards. To prevent those reviewers who could somehow score cards in partnership with retailers, NVIDIA ensured there was no driver available until earlier today. Without drivers, there's no way for anyone to test the card, and it shows—we've scoured the web, and nobody has a review. There should be cards available in retail already, but only listings with "out of stock", "coming soon" have appeared so far. We do intend to buy one off the shelf and test it for you with the first available driver. As of this writing, we cannot find any of these cards in the online retail.Update 15:16 UTC: We've reached out to several shops here in Germany, they all confirmed that "the embargo expired today at 3 pm", but also mentioned that "the on-shelf availability date is unknown".

Update Jul 19th: First merchants in Germany have received a handful of cards, there's still no stock in UK or USA.

Update Jul 24th: We've bought a RTX 4060 Ti 16 GB in retails and posted our full in-depth review here.

USA retailer, Newegg, is currently running a sale on a couple of custom NVIDIA GeForce RTX 4060 Ti 8 GB graphics cards. The cheapest option is an MSI VENTUS 2X BLACK 8G OC model, available for an an-all-time low price of $334 (representing a nice 16% discount)—thanks to a promo code ("ZIPTECH") shaving off a further $45.60 from the sale price of $379.99. NVIDIA set an MSRP of $399.99 upon the GeForce RTX 4060 Ti's launch back in late May, generating plenty of ambivalence within the PC hardware enthusiast community. That pattern will likely repeat with next week's premiere of RTX 4060 Ti 16 GB variants—its recommended retail price is set at $499, with tricked out custom cards predicted to go beyond $550.

Potential buyers of the bog standard 8 GB GPU in the States will be somewhat happy to discover that Newegg is not limiting the sale and discounts to a single model. MSI's slightly fancier (triple fan design) VENTUS 3X 8G OC card is going for $351.99, and the GIGABYTE RTX 4060 Ti EAGLE plus ASUS RTX 4060 Ti DUAL OC are available at the same price. These deals look quite good when placed next to discounted GeForce RTX 3060 Ti 8 GB custom cards—these are getting blown out for $329 - 339.

EK, the leading computer cooling solutions provider, now offers EK-Pro GPU WB RTX 6000 Ada Rack - Nickel + Inox, an enterprise-grade full-cover water block meticulously designed for Nvidia RTX 6000 Ada Generation graphics cards. Crafted to excel in rack mount environments, this cutting-edge water block leverages the power of the Nvidia Ada Lovelace Architecture. Its exceptional construction showcases a CNC-machined nickel-plated copper base, complemented by a laser-cut stainless-steel top, creating a resilient liquid cooling solution that effectively transforms into a space-saving single-slot assembly. It encompasses the entire GPU, VRAM, and VRM components, precisely channeling the cooling liquid over these critical areas to efficiently dissipate heat.

Rack Mount Form Factor
The EK-Pro GPU WB RTX 6000 Ada Rack - Nickel + Inox is a purpose-built water block allowing you to have a professionally liquid-cooled Nvidia RTX 6000 Ada Generation graphics card, perfectly suited for server rack installations. Designed to seamlessly integrate into standard Full Height Full Width (FHFW) server chassis form factors, these EK-Pro Rack GPU water blocks serve as convenient drop-in replacements for both active and passive dual-slot air coolers.

Leaked photos of a cinder block-sized NVIDIA flagship graphics card cooler appeared online over a week ago, with speculation pointing to it originating from an extremely powerful RTX-40 series GPU—perhaps a theoretical GeForce RTX 4090 Ti or something codenamed TITAN ADA. The pictured prototype outsizes several existing reference designs—its substantial bulk could be enough to tame the fully unlocked potential of Team Green's already large AD102.

Last week's photos have been traced back to the source—as reported by Wccftech, it seems that a seller on the Chinese Taobao Goofish platform is attempting to flog the unit for roughly $122,750 (888,888 RMB). The seller/site member "Hayaka" is apparently open to accepting offers from the highest bidder, but the prospective buyer will not be getting their hands on any working hardware—the listing is for the cooler alone. No GPU or PCB is included according to the provided information, so the winner will be procuring a very expensive (albeit highly unique) mantelpiece.

GIGABYTE TECHNOLOGY Co. Ltd, a leading manufacturer of premium gaming hardware, today launched the GeForce RTX 4060 series graphics cards powered by NVIDIA Ada Lovelace architecture, including DLSS 3 neural rendering and third-generation ray tracing technologies at high frame rates. The cards will be available on June 29. GIGABYTE's GeForce RTX 4060 Series includes five models with the WINDFORCE thermal solution, the AORUS GeForce RTX 4060 ELITE 8G, the GeForce RTX 4060 AERO OC 8G, the GeForce RTX 4060 GAMING OC 8G, the GeForce RTX 4060 EAGLE OC 8G and the GeForce RTX 4060 WINDFORCE OC 8G graphics cards. All the models provide gamers with diverse choices to enjoy the AAA gaming experience. All graphics cards from GIGABYTE are perfectly tuned with powerful performance, low temperature, and quietness at once, bringing gamers an ultimate gaming experience.

AORUS GeForce RTX 4060 ELITE 8G
AORUS GeForce RTX 4060 ELITE 8G graphics card stands out for the powerful cooling capabilities and outstanding performance, it's the top-tier gaming graphics card pursued by gamers and fans. The AORUS graphics card features the famous RGB Halo which takes advantage of the persistence of human vision to create exclusive lighting effects via rotating fans. The exquisite and colorful illumination RGB, favored by AORUS fans and DIY enthusiasts, allows gamers to customize its colors through the GIGABYTE CONTROL CENTER software with ease.

NVIDIA GeForce RTX 4060 "Ada" started selling today, with its baseline price at USD $299. The swanky new performance segment graphics card is meant to succeed the popular RTX 3060 "Ampere," offering around 10-20% higher performance, at 50% lower power-draw thanks to the 5 nm foundry process. The card sports the new DLSS 3 Frame Generation feature that nearly doubles performance at comparable image quality, as it generates entire alternate frames entirely using AI, without involving the graphics rendering machinery. NVIDIA is ensuring its board partners have products at the $299 MSRP, most of the premium overclocked RTX 4060 cards are priced $20-40 higher, with the notable exception of the ASUS ROG Strix, which is going for $389, just short of the RTX 4060 Ti MSRP.

Be sure to check out our large selection of reviews that include:

ASUS RTX 4060 DUAL OC | ASUS ROG Strix RTX 4060 OC | MSI RTX 4060 Gaming X | MSI RTX 4060 Ventus 2X | Gigabyte RTX 4060 WindForce OC | Gigabyte RTX 4060 Gaming OC | Galax RTX 4060 EX | Palit RTX 4060 Dual OC | PNY RTX 4060 XLR8 OC | Zotac RTX 4060 Spider-Man

According to the NVIDIA roadmap that was spotted in the recently published MLCommons training results, the Ada Lovelace successor is set to come in 2025. The roadmap also reveals the schedule for Hopper Next and Grace Next GPUs, as well as the BlueField-4 DPU.

While the roadmap does not provide a lot of details, it does give us a general idea of when to expect NVIDIA's next GeForce architecture. Since NVIDIA usually launches a new GeForce architecture every two years or so, the latest schedule might sound like a small delay, at least if it plans to launch the Ada Lovelace Next in early 2025 and not later. NVIDIA Pascal was launched in May 2016, Turing in September 2018, Ampere in May 2020, and Ada Lovelace in October 2022.

ZOTAC Technology Limited, a leading global manufacturer of innovation, announces additional members to its next-generation graphics card line-up, built on the powerful NVIDIA Ada Lovelace architecture. The GeForce RTX 4060 8 GB series is designed to deliver incredible performance for mainstream gamers and creators at 1080p resolution with Ray Tracing and DLSS 3 at high frame rates. The GeForce RTX 4060 8 GB graphics card delivers all the advancements of the NVIDIA Ada Lovelace architecture—including DLSS 3 neural rendering, third-generation ray tracing technologies, and an eighth generation NVIDIA Encoder (NVENC) with AV1 encoding.

ZOTAC had announced the ZOTAC GAMING GeForce RTX 4060 8 GB SOLO graphics card as a part of the initial lineup of the 4060 Family. Today, ZOTAC unveils two additional GeForce RTX 4060 8 GB models: the TWIN EDGE OC WHITE EDITION and the OC Spider-man: Across the Spider-Verse inspired bundle. The ZOTAC GAMING GeForce RTX 4060 8 GB TWIN EDGE OC WHITE EDITION combines ZOTAC's signature aerodynamic-inspired design with minimalistic and clean style, while also featuring the highest clock speed out of ZOTAC GAMING's 4060 8 GB selection. This pure-white, dual-fan graphics card epitomizes form, utility and style, letting gamers add just the right touch of personality and beauty to their gaming builds.

Back in January, we got our first look at the cinder block-like 4-slot cooling solution of NVIDIA's upcoming flagship graphics card (called either the RTX 4090 Ti, or the TITAN (Ada). "ExperteVallah" on Twitter scored additional pictures of the cooler. Its design sees the heat dissipation surface pushed to the entire thickness of the cooler, and ventilated the entire length.

The card's PCB isn't conventional—not perpendicular to the plane of the motherboard like any other add-in card—but is rather along the plane of the motherboard, with additional breakaway daughter cards interfacing with the sole 12VHPWR power connector, and the PCIe slot. This slender, ruler-shaped PCB spans the entire length of the card, without coming in the way of its heat dissipation surfaces. The length is used for the large AD102 ASIC that's probably maxed out (with all its 144 SM enabled), twelve GDDR6X (possibly faster 23 Gbps), and a mammoth VRM that nearly maxes out the 600 W continuous power delivery design limit of the 12VHPWR.

GIGABYTE released liquid-cooled graphics cards based on the performance-segment GeForce RTX 4070 Ti. The company is catering to both the DIY liquid cooling and turnkey liquid cooling market segments with the RTX 4070 Ti AORUS Xtreme WaterForce series. The RTX 4070 Ti AORUS Xtreme WB comes with a factory-fitted full-coverage water block that you connect to your own liquid-cooling loop; while the RTX 4070 Ti AORUS Xtreme lugs an AIO liquid cooling solution.

The AORUS Xtreme WaterForce WB uses a nickel-plated copper full-coverage water block that's been tailored for the PCB layout underneath, with an acrylic top, and some vinyl decals. The acrylic top is studded with addressable RGB LEDs. The AORUS Xtreme WaterForce (AIO based) card, on the other hand, uses an AIO cooling solution with a design resembling that of the company's RTX 3080 AORUS Xtreme WaterForce. This card uses a purely-liquid cooling solution (unlike some other brands with an air+liquid hybrid design). The pump-block in the card is responsible not just for the GPU, but also the memory and VRM (over secondary base-plates). A 240 mm x 120 mm radiator is used, which should be just about enough for a 300 W TGP graphics card. GIGABYTE could formally launch these two cards very soon, as the press images are already out.

NVIDIA could be advancing the launch of its GeForce RTX 4060 (non-Ti) graphics card from its July 2023 launch the company originally announced. Leaked documents shared by MEGAsizeGPU say that NVIDIA could make the RTX 4060 available on June 29, which means reviews of the card could go live on June 28 for the MSRP cards, and June 29 for the premium ones priced above MSRP. It was earlier expected to launch alongside the 16 GB variant of the RTX 4060 Ti, in July.

The RTX 4060 is a significantly different product from the RTX 4060 Ti the company launched in May, it is based on the smaller AD107 silicon. The card is expected to feature 3,072 CUDA cores, 24 RT cores, 96 Tensor cores, 96 TMUs, and 32 ROPs, compared to the 4,352 CUDA cores, 34 RT cores, 136 Tensor cores, 136 TMUs, and 48 ROPs, of the RTX 4060 Ti. The memory configuration is similar, with 8 GB of GDDR6 memory across a 128-bit wide memory bus, however, the memory speed is slightly lower, at 17 Gbps vs. 18 Gbps of the Ti. The RTX 4060 has a TGP of just 115 W. The company hasn't finalized its price, yet.Update Jun 14th: NVIDIA confirmed the launch date on Twitter:

NVIDIAThe GeForce RTX 4060 will now be available to order starting June 29, at 6AM Pacific.

EK, the leading computer cooling solutions provider, is unveiling the EK-Pro GPU WB RTX 6000 Ada - Nickel + Inox. This enterprise-grade full-cover water block is designed specifically for the NVIDIA RTX 6000 Ada Generation graphics card built on the NVIDIA Ada Lovelace Architecture.

The water block features a meticulously CNC-machined nickel-plated copper base and a laser-cut stainless-steel top for a robust liquid cooling solution. It encompasses the entire GPU, VRAM, and VRM components, precisely channeling the cooling liquid over these critical areas to efficiently dissipate heat. The EK-Pro GPU WB RTX 6000 Ada - Nickel + Inox is engineered to deliver superior cooling efficiency, unlocking the full potential of the NVIDIA RTX 6000 Ada graphics card.

According to a new research report from the analyst firm Jon Peddie Research, unit shipments in the add-in board (AIB) market decreased in Q1 2023 by -12.6% and decreased by -38.2% year to year. Intel increased its add-in board market share by 2% during the first quarter.

The percentage of AIBs in desktop PCs is referred to as the attach rate. The attach rate grew from last quarter by 8% but was down -21% year to year. Approximately 6.3 million add-in boards shipped in Q1 2023. The market shares for the desktop discrete GPU suppliers shifted in the quarter, as AMD's market share remained flat from last quarter. Intel, which entered the AIB market in Q3'22 with the Arc A770 and A750, gained 2% in market share, while Nvidia retains its dominant position in the add-in board space with an 84% market share.

Increasing its HPL score from 1.02 Eflop/s in November 2022 to an impressive 1.194 Eflop/s on this list, Frontier was able to improve upon its score after a stagnation between June 2022 and November 2022. Considering exascale was only a goal to aspire to just a few years ago, a roughly 17% increase here is an enormous success. Additionally, Frontier earned a score of 9.95 Eflop/s on the HLP-MxP benchmark, which measures performance for mixed-precision calculation. This is also an increase over the 7.94 EFlop/s that the system achieved on the previous list and nearly 10 times more powerful than the machine's HPL score. Frontier is based on the HPE Cray EX235a architecture and utilizes AMD EPYC 64C 2 GHz processors. It also has 8,699,904 cores and an incredible energy efficiency rating of 52.59 Gflops/watt. It also relies on gigabit ethernet for data transfer.

The "AD107" is expected to be the smallest client GPU based on the NVIDIA "Ada Lovelace" graphics architecture. The upcoming GeForce RTX 4060 (non-Ti) is rumored to be maxing this silicon out (enabling all available shaders). MEGAsizeGPU scored one of the first pictures of the "AD107" in the flesh, revealing a small fiberglass substrate, and a visibly smaller die than the "AD106" powering the RTX 4060 Ti.

The "AD107" silicon is expected to feature 3,072 CUDA cores across 24 SM (streaming multiprocessors). The GPU features a 128-bit wide memory interface much like the "AD106," and NVIDIA is expected to use conventional 17 Gbps GDDR6 memory, which works out to 272 GB/s memory bandwidth. 8 GB is the standard memory size for the RTX 4060. With "Ada," NVIDIA has rebalanced the memory sub-system with greater reliance on on-die caches, and the "AD107" features a 24 MB L2 cache. Much like the "AD106," the smaller "AD107" features a PCI-Express 4.0 x8 host interface. The ace up its sleeve has to be power, with even the maxed out RTX 4060 only being rated for 119 W of TGP.

ASUS today announced NVIDIA GeForce RTX 4060 and 4060 Ti graphics cards for the ROG Strix, TUF Gaming and ASUS Dual families, delivering the latest NVIDIA architecture and cutting-edge tech such as DLSS 3 frame generation to mainstream gamers. The RTX 4060 Ti graphics cards will be the frontrunners for this series, and they will ship with a healthy 8 GB of VRAM. At a later date, ASUS will also launch variants of the ROG Strix, TUF Gaming, Dual, and Dual White RTX 4060 Ti graphics cards equipped with an even-larger 16 GB pool of VRAM. The extra helping of memory will give gamers with a taste for cutting-edge graphics extra headroom to dial up high-resolution textures and high-end visual effects in demanding games.

The ROG Strix GeForce RTX 4060, TUF Gaming GeForce RTX 4060, ASUS Dual GeForce RTX 4060 and ASUS Dual White GeForce RTX 4060 are also coming at a later date. ASUS will share all the details on these graphics cards soon, so gamers will not have to wait long to learn more about them—or make one their own. These GeForce RTX 4060 Ti and RTX 4060-powered GPUs are designed to deliver incredible performance for mainstream gamers and creators at 1080p resolution at 100 frames per second with ray tracing and DLSS 3. The GeForce RTX 4060 product family delivers all the advancements of the NVIDIA Ada Lovelace architecture—including DLSS 3 neural rendering, third-generation ray tracing technologies at high frame rates, and an eighth-generation NVIDIA Encoder (NVENC) with AV1 encoding.

GIGABYTE TECHNOLOGY Co. Ltd, a leading manufacturer of premium gaming hardware, today launches NVIDIA GeForce RTX 4060 Ti 16 GB, GeForce RTX 4060 Ti 8 GB and GeForce RTX 4060 8 GB series graphics cards powered by NVIDIA ADA Lovelace architecture. GIGABYTE offers a wide range of graphics cards, including the AORUS and GIGABYTE series, to cater to the diverse needs of gamers. These cards are designed to meet the demands of gamers seeking the ultimate in performance and stunning aesthetics, as well as those who prioritize fundamental performance and durability. These graphics cards will enhance the gaming experience for a vast number of gamers.

The GeForce RTX 4060 family is designed to deliver incredible performance for mainstream gamers and creators at 1080p resolution at 100 frames per second with Ray Tracing and DLSS 3. The GeForce RTX 4060 product family delivers all the advancements of the NVIDIA Ada Lovelace architecture—including DLSS 3 neural rendering, third-generation ray tracing technologies at high frame rates, and an eighth generation NVIDIA Encoder (NVENC) with AV1 encoding.

NVIDIA today announced the GeForce RTX 4060 family of GPUs, with two graphics cards that deliver all the advancements of the NVIDIA Ada Lovelace architecture—including DLSS 3 neural rendering and third-generation ray tracing technologies at high frame rates—starting at just $299. The GeForce RTX 4060 Ti and GeForce RTX 4060 deliver unparalleled performance at fantastic value—bringing for the first time to the company's popular 60-class twice the horsepower of the latest gaming consoles, including ray tracing for premium image quality on top games.

"The RTX 4060 family delivers PC gamers both great value and great performance at 1080p, whether they're building a gaming battle box or an AI-assisted creation station," said Matt Wuebbling, vice president of global GeForce marketing at NVIDIA. "These GPUs deliver an incredible upgrade, starting at just $299, putting Ada Lovelace and DLSS 3 in the hands of millions more worldwide."

VideoCardz struck the mother lode with information on the upcoming NVIDIA GeForce RTX 4060 Ti and RTX 4060 "Ada" graphics cards, by scoring key slides from the NVIDIA press-deck. But first, the prices: When it goes on sale later this month, the GeForce RTX 4060 Ti will be priced at USD $399. Its 16 GB sibling goes on sale in July, priced at $499. The company didn't finalize the pricing of the RTX 4060, yet. Without disclosing the CUDA core count (rumored to be 4,352), NVIDIA revealed that the RTX 4060 Ti has a shader compute throughput of 22 TFLOP/s, which is 37.5% higher than that of the RTX 3060 Ti.

The specs also confirm that the RTX 4060 Ti has a significantly narrower memory bus, at 128-bit, compared to the 256-bit of the RTX 3060 Ti, and 192-bit of the RTX 4060. With "Ada," NVIDIA overhauled the memory sub-system of the GPU, with greater on-die cache reliance, which allows the company to use narrower memory interfaces and cut costs. Both memory variants of the RTX 4060 Ti come with a TGP of 160 W. which means even the faster custom-design boards should be able to make do with a single 8-pin PCIe power connector. The GeForce RTX 4060 is designed with 15% higher shader throughput than the previous-generation RTX 3060, which is 6% shy of the RTX 3060 Ti. The most striking aspect of this card is its TGP of just 115 W, which should make it technically possible to have cards with even single 6-pin PCIe power connectors.

The NVIDIA RTX 4000 SFF Ada Generation graphics card was released to the public in late April, but very few reviews and benchmarks have emerged since then. Jisaku Hibi, a Japanese hardware site, has published an in-depth evaluation that focuses mostly on gaming performance. The RTX 4000 Ada SFF has been designed as a compact workstation graphics card, but its usage of an AD104 die makes it a sibling of NVIDIA's GeForce RTX 4070 and 4070 Ti gaming-oriented cards. Several PC hardware sites have posited that the 70 W RTX 4000 Ada SFF would "offer GeForce RTX 3070-like performance," but Jisaku Hibi's investigation points to the RTX 3060 Ti being the closest equivalent card (in terms of benchmark results).

According to the TPU GPU database: "NVIDIA has disabled some shading units on the RTX 4000 SFF Ada Generation to reach the product's target shader count. It features 6144 shading units, 192 texture mapping units, and 80 ROPs. Also included are 192 tensor cores which help improve the speed of machine learning applications. The card also has 48 ray tracing acceleration cores. NVIDIA has paired 20 GB GDDR6 memory with the RTX 4000 SFF Ada Generation, which are connected using a 160-bit memory interface. The GPU is operating at a frequency of 1290 MHz, which can be boosted up to 1565 MHz, memory is running at 1750 MHz (14 Gbps effective)." The SKU's 70 W TGP and limited memory interface are seen as the card's main weak points, resulting in average clock speeds and a maximum memory bandwidth of only 280 GB/s.