As a leading brand in True Gaming hardware, MSI is excited to announce the availability for the RTX 4080 and RTX 4070 Ti based GAMING TRIO WHITE graphics cards. The new WHITE series unite the latest in graphics technology, high-performance circuit board design, and advanced cooling in a fabulous silver & white finish. Besides being perfectly tuned for keeping temperatures low while staying virtually silent, these new cards are the perfect choice for white or silver builds by DIY builders everywhere.

Just like the standard MSI GeForce RTX 4080 16 GB and RTX 4070 Ti GAMING TRIO cards, the WHITE edition features the same great balance between performance, cooling, and low noise that gamers have come to trust. Sporting three white versions of the latest TORX Fan 5.0 design, which uses pairs of three fan blades bound together with an outer link to form a rim that focuses airflow into the upgraded TRI FROZR 3 cooling system. The proven nickel-plated copper baseplate at the heart of the heatsink assists to dissipate the heat effectively. The new GAMING TRIO WHITE series are also fitted with a Dual BIOS, giving easy access to profiles that prioritize low noise or more performance with the flick of a switch. A frosty white & silver version of the metal backplate with a flow-through design reinforces the graphics card, while also providing passive cooling action through the implementation of thermal pads. Mystic Light adorns the exterior of the graphics card, illuminating color in synchrony with the rest of the PC through Mystic Light Sync and Ambient Link. As a finishing touch, these cards even come with a white version of the GAMING TRIO support bracket. Combined with other components from MSI's white product line, an impeccable white build can be achieved.

ZOTAC Technology Limited, a global manufacturer of innovation, announces the latest in the next-generation ZOTAC GAMING graphics card line-up built on the powerful NVIDIA Ada Lovelace architecture. The GeForce RTX 4070 Ti Series graphics cards are beyond fast, giving gamers and creators new found levels of performance in gaming, streaming, rendering, video encoding and decoding, neural rendering, and many more leading platform capabilities. These GPUs push state-of-the-art graphics into the future with technologies including 3rd generation ray tracing cores and 4th generation tensor cores powering DLSS 3 technology that are gateways to the most immersive gaming experiences.

Leveraging an all-new aerodynamic inspired design with a bevy of powerful features, the ZOTAC GAMING GeForce RTX 4070 Ti Series carry over many key innovations introduced in the 4090 series that push the limit in gaming performance, cooling efficiency, noise levels and durability. The ZOTAC GAMING GeForce RTX 4070 Ti features 12 GB GDDR6X GPU memory and will come in 4 models - AMP Extreme AIRO, the debut of the all-new AMP AIRO, Trinity OC, and Trinity.

A leaked NVIDIA company slide confirms that the upcoming GeForce RTX 4070 Ti graphics card will launch at a starting price of USD $799. This would put it $100 cheaper than what was going to be the launch price of the RTX 4080 12 GB. NVIDIA cancelled the launch of the RTX 4080 12 GB, and reportedly re-branded it to the RTX 4070 Ti. The RTX 4080 12 GB was supposed to launch alongside the RTX 4080 16 GB in mid-November 2022, but the company decided to "unlaunch" it, in the wake of bad press on the confusing and deceptive naming of the SKU, and its ambitious MSRP that would have put custom-design cards well above the $1,000-mark.

The NVIDIA slide goes on to claim that the RTX 4070 Ti will be faster than the previous-generation flagship, the RTX 3090 Ti. This is thanks to its 40 shader TFLOP/s, 93 RT TFLOP/s, and 642 Tensor TFLOP/s. The RTX 4070 Ti is expected to debut the new 4 nm "AD104" silicon, featuring 7,680 CUDA cores, 60 RT cores, 240 Tensor cores, 240 TMUs, and 80 ROPs. The card features 12 GB of 21 Gbps GDDR6X memory across a rather narrow 192-bit memory bus. The slide confirms that January 5, 2023 will be the market availability date for the RTX 4070 Ti. NVIDIA's decision to price the RTX 4070 Ti at $799 may have been influenced by the AMD Radeon RX 7900 XT priced at $899.

With less than a week to go until the official launch of the GeForce RTX 4070 Ti, NVIDIA France has gone and spoiled things by revealing the official specs of the upcoming GPU. The French division of NVIDIA appears to have posted the full product page, but it has since then been pulled. That didn't prevent Twitter leaker @momomo_us from snapping a couple of screenshots, including that of the official performance numbers from NVIDIA.

There aren't any real surprises here though, as we already knew the CUDA core count and the memory size, courtesy of the RTX 4070 Ti having been the RTX 4080 12 GB, until NVIDIA changed its mind. It's interesting to see that NVIDIA compares the RTX 4070 Ti to the RTX 3080 12 GB in the three official benchmarks, as it makes the RTX 4070 Ti look a lot better than it is in reality, at least based on the rumoured MSRP of US$800-900. One of the three benchmarks is Cyberpunk 2077 using Raytracingl, where NVIDIA suggests the RTX 4070 Ti is around 3.5 times faster than the RTX 3080, but it's worth reading the fine print. We'll know next week how the RTX 4070 Ti actually performs, as well as where the official pricing and actual retail pricing ends up.

VideoCardz has obtained images and specifications of PNY's two upcoming GeForce RTX 4070 Ti models. According to the latest leak, these GPUs are equipped with 7680 CUDA cores and 12 GB of GDDR6X memory. This configuration resembles the canceled GeForce RTX 4080 12 GB edition card, which confirms that NVIDIA will rebrand it under the RTX 4070 Ti naming scheme. PNY has prepared GeForce RTX 4070 Ti XLR8 VERTO and VERTO GPUs, with the difference in cooler design and applied factory overclocking. The XLR8 version bears the same cooler as the RTX 4080 XRL8 card, adapted for the RTX 4070 Ti GPU SKU. This design should naturally offer greater overclocking performance than the regular VERTO SKU.

The render below looks like the 16-pin 12VHPWR power connector remains on these cards and that PNY has not swapped it for another solution. We expect to hear more about these cards on January 5th, when NVIDIA plans to launch.

NVIDIA's upcoming GeForce RTX 4070 Ti performance-segment graphics card could see a January 5, 2023 launch (the day on which you can buy one), according to a Wccftech report. The card will be unveiled to the masses on January 3, and reviews of the card could go live on January 4, before product-availability the next day. This would mean that reviewers could get the card well in advance, and would probably be testing it over the Christmas break in order to meet the review date, before flying off to the 2023 International CES, which opens to the public on January 5, and to the press a couple of days earlier.

The GeForce RTX 4070 Ti is reportedly a rebadged RTX 4080 12 GB, which was supposed to launch alongside the RTX 4080 16 GB on November 16; before NVIDIA pulled the plug on the SKU in the face of backlash on social media and the press over its controversial naming that could confuse buyers, given its significantly different hardware specs to those of the RTX 4080 16 GB. With the first batch of RTX 4080 12 GB cards probably already boxed and ready to ship, if not shipped already, NVIDIA is issuing re-branding guidelines to its board partners, so they could do their best at pasting stickers, a template of which is below. It remains to be seen if NVIDIA sticks to the $900 MSRP for the SKU.

Apple today announced the new iPad Pro with the M2 chip, delivering the ultimate combination of portability, versatility, and unbelievable performance. The new iPad Pro features a next-level Apple Pencil hover experience and superfast wireless connectivity, along with the world's most advanced mobile display, pro cameras, Face ID, Thunderbolt, and a four-speaker audio system. New features in iPadOS 16—including Stage Manager, full external display support, desktop-class apps, and Reference Mode—take pro workflows on iPad even further. Enabled by its advanced hardware and iPadOS 16, iPad Pro has an incredible ecosystem of powerful pro apps unlike any other device of its kind. The new iPad Pro is available to order starting today, and in stores beginning Wednesday, October 26.

"The next-generation iPad Pro pushes the boundaries of what's possible on iPad, bringing even more versatility, power, and portability to the ultimate iPad experience," said Greg Joswiak, Apple's senior vice president of Worldwide Marketing. "Powered by the M2 chip, the new iPad Pro features incredible performance and the most advanced technologies, including a next-level Apple Pencil hover experience, ProRes video capture, superfast wireless connectivity, and powerful iPadOS 16 features. There's nothing else like it."

ASUS Republic of Gamers (ROG) today premieres Dare to be Ultimate: Building a World-Leading Gaming Phone, the design story video that reveals the genesis of the new ROG Phone 6D series of gaming smartphones. The ROG Phone 6D and ROG Phone 6D Ultimate are powered by the latest flagship MediaTek Dimensity 9000+ 5G chipset. Clocking up to 3.2 GHz CPU speeds, and boasting up to 16 GB of LPDDR5X RAM and 512 GB ROM of storage, the Dimensity 9000+ chipset provides flagship 5G experiences, perfect for mobile gamers.

"The pursuit of the ultimate performance and gaming experience has always been central for the ROG Phone. With each iteration, we consistently strive to surpass ourselves, achieving the spirit of For Those Who Dare," said S.Y. Hsu, Co-CEO, ASUS. "We are thrilled that this first collaboration with MediaTek has achieved such stunning performance, and we will continue to strive for continuous performance improvements."

Remember that Limited Edition card that Intel was teasing at the end of March? Well, it turns out that it could very well be the Arc A750 card, at least based on a quick appearance of a card in Gamer Nexus' review of the Gunnir Arc A380 card. For a few seconds in the review video, Gamers Nexus was showing off a card that looked nigh on identical to the renders Intel showed back in March. There was no mention of any specs or anything else related, except that Gamer Nexus has tested the card and that it will presumably be getting its own video in the near future based on what was said in the video.

Based on leaked information, the Arc A750 GPU should feature 24 Xe cores, 3072 FP32 cores and it's expected to be paired with 12 GB of GDDR6 memory on a 192-bit bus. For reference, the Arc A380 features eight Xe cores, 1024 FP32 cores and the cards ship with 6 GB of GDDR6 memory on a 96-bit bus. In related news, Intel is said to be touring some gaming events in the US promoting its yet unavailable Arc graphics cards. LANFest Colorado is said to be the first stop, so if you're planning on attending, this could be your first chance to get some hands-on time with an Arc graphics card.

Intel's upcoming Arc Alchemist lineup of discrete graphics cards generates a lot of attention from consumers. Leaks of these cards' performance and detailed specifications appear more and more as we enter the countdown to the launch day, which is sometime in Q1 of this year. Today, we managed to see a slide from @9950pro on Twitter that shows the laptop memory configuration of Intel's DG2 GPU. As the picture suggests, we can see that the top-end SKU1 with 512 EUs supports a 16 GB capacity of GDDR6 memory that runs at 16 Gbps speeds. The memory runs on a 256-bit bus and generates 512 GB/s bandwidth while having eight VRAM modules present.

When it comes to SKU2, which is a variant with 384 EUs, this configuration supports six VRAM modules on a 192-bit bus, running at 16 Gbps speeds. They generate a total capacity of 12 GBs and a bandwidth of 384 GB/s. We have SKU3 DG2 GPU going down the stack, featuring 256 EUs, four VRAM modules on a 128-bit bus, 8 GB capacity, and a 256 GB/s bandwidth. And last but not least, the smallest DG2 variants come in the form of SKU4 and SKU5, feating 128 EUs and 96 EUs, respectively. Intel envisions these lower-end SKUs with two VRAM modules on a 64-bit bus, and this time slower GDDR6 memory running at 14 Gbps. They are paired with 4 GB of total capacity, and the total bandwidth comes down to 112 GB/s.

GIGABYTE TECHNOLOGY Co. Ltd, a leading manufacturer of premium gaming hardware, today announced the upgraded versions of GeForce RTX 3080 graphics cards with 12 GB of VRAM. GIGABYTE provides consumers with a variety of series to meet the needs of more customers. The AORUS series is recommended for the enthusiasts who want the ultimate performance and colorful RGB appearance. The GAMING OC series is the best choice of performance-minded gamers. The EAGLE series is the best choice for those who desire a unique design. In addition to the excellent cooling system and distinctive appearance of each series of graphics cards, they have been upgraded to a larger 12 GB memory capacity to meet the needs of latest graphics intensive 4K game and heavy-duty 3D creation.

The AORUS GeForce RTX 3080 MASTER 12G graphics card is equipped with the MAX-Covered cooling system that features three unique blade fans with a wind claw design and alternate spinning to deliver optimal airflow across the entire heatsink. The large heat-sink and a large vapor chamber and the multiple composite heat-pipes enable heat from the GPU and VRAM to dissipate quickly. Coupled with GIGABYTE's screen cooling technology, the extended heatsink fins allow air to pass through, forming an extremely efficient heat dissipation system to ensure stable operation. A powerful LCD monitor and RGB Fusion 2.0 allows gamers to enjoy various display modes and lighting effects. It is recommended for enthusiasts who want the ultimate 4k gaming performance with colorful RGB lighting.

During the CES 2022 keynote, we have witnessed NVIDIA update its GeForce RTX 30 series family with GeForce RTX 3050 and RTX 3090 Ti. However, this is not an end to NVIDIA's updates to the Ampere generation, as we now hear industry sources from Wccftech suggest that we could see a GeForce RTX 3080 GPU with 12 GB of GDDR6X VRAM enabled, launched as a separate product. Compared to the regular RTX 3080 that carries only 10 GB of GDDR6X, the new 12 GB version is supposed to bring a slight bump up to the specification list. The GA102-220 GPU SKU found inside the 12 GB variant will feature 70 SMs with 8960 CUDA, 70 RT cores, and 280 TMUs.

This represents a minor improvement over the regular GA102-200 silicon inside the 8 GB model. However, the significant difference is the memory organization. With the new 12 GB model, we have a 384-bit memory bus allowing GDDR6X modules to achieve a bandwidth of 912 GB/s, all while running at 19 Gbps speeds. The overall TDP will also receive a bump to 350 Watts, compared to 320 Watts of the regular RTX 3080 model. For more information regarding final clock speeds and pricing, we have to wait for the alleged launch date - January 11th.

The RTX 3080 12 GB is still a rumored card, despite the increasing amounts of evidence towards its eventual release. The card's refreshed VRAM amount in particular seems to be an important part of NVIDIA's competitiveness plan, not only against AMD's RX 6000-series, which sport a psychological (and sometimes practical) advantage with their 16 GB VRAM capacities; but against Intel and its upcoming ARC Alchemist launch, which are expected to also offer 16 GB of VRAM at competitive shading performance levels.

But it seems that NVIDIA's refresh of the RTX 3080 graphics card won't be limited to a VRAM and bus width increase - CUDA core counts are now reported to have also increased by 2.9%, up to 8,960 from the RTX 3080 10 GB's 8,704 CUDA cores. The card is naturally still expected to make use of the GA-102 chip. An expected increased memory bus width of 384-bits will also bring about an increase in memory bandwidth, at 912 GB/s, the same as the RTX 3080 Ti (it stands at 760 GB/s for the RTX 3080).

MSI introduced its first two graphics cards on the necromanced GeForce RTX 2060 12 GB, The new RTX 2060 12 GB SKU formally launched on December 7, and pairs features 2,176 CUDA cores (compared to 1,920 on the original RTX 2060). It uses 12 GB of GDDR6 memory across a 192-bit wide memory bus, which is what separates it from the RTX 2060 SUPER. MSI is pairing it with the company's latest iteration of the Ventus 2X dual-fan cooling solution. The RTX 2060 12 GB Ventus sticks to NVIDIA-reference clock speeds of 1650 MHz boost; while the factory-overclocked Ventus OC runs the GPU at 1710 MHz boost. The memory is untouched on both cards at 14 Gbps. We have no prices at hand for the RTX 2060 12 GB, since NVIDIA didn't put out any SEP. We've seen these cards go for around $550.

INNO3D, a leading manufacturer of pioneering high-end multimedia components and innovations today announces the upgraded INNO3D NVIDIA GeForce RTX 2060 TWIN X2 OC now with 12 GB. Improving performance and power efficiency over previous models of the RTX 2060 family, the INNO3D GeForce RTX 2060 12 GB lets the gamer now enjoy faster, smoother gameplay, supporting the latest DirectX 12 Ultimate that features in both classic and latest game titles. The new GeForce RTX 2060 12 GB brings the incredible performance and power of real-time ray tracing and AI to the latest games—and every gamer.

Founded in 1998 with the vision of developing pioneering computer hardware products on a global scale. Fast forward to the present day, INNO3D is now well-established in the gaming community known for our innovative and daring approach to design and technology. We are Brutal by Nature in everything we do and are 201% committed to you for the best gaming experience in the world.

NVIDIA today released the GeForce 497.09 Game Ready drivers. These introduce launch-day optimization for "Icarus," including support for NVIDIA DLSS, and RTX ray-traced global illumination (RTX-GI). The drivers also add optimization for "Chorus," including DLSS support; and "Halo Infinite." Six new displays receive NVIDIA G-SYNC support. Among the fixes released with these drivers are TDR or system crashes with "DOOM Eternal" and RDR2, a display corruption with ye olde "DOOM 3 BFG Edition," extreme gamma/contrast issues with YouTube on hardware-accelerated web-browsers; NVIDIA Image Scaling resolutions not correctly appearing in-game after a driver update; and incompatibilities between Adaptive Sync and G-SYNC.

A curious addition with these drivers is support for the GeForce RTX 2060 12 GB graphics card. We've been hearing reports of NVIDIA resurrecting the RTX 2060 "Turing" with 12 GB of GDDR6 memory to target the 1080p gaming crowd; and these drivers confirm it. The 12 GB SKU could be achieved by pairing the "TU106" GPU with 12 GB of memory across its 192-bit wide memory interface.

DOWNLOAD: NVIDIA GeForce 497.09 WHQL

The on-again, off-again relationship between NVIDIA and its Turing-based RTX 2060 graphics seems to be heading towards a new tipping point. As previously reported, NVIDIA is expected to be preparing another release cycle for its RTX 2060 graphics card - this time, paired with an as puzzling as it is gargantuan (for its shader performance) 12 GB of GDDR6 memory. Gigabyte has given us yet another tip at the card's expected launch by the end of this year or early 2022 by registering four different card models with the EEC (Eurasian Economic Commission). Gigabyte's four registered cards carry the model numbers GV-N2060OC-12GD, GV-N2060D6-12GD, GV-N2060WF2OC-12GD, and GV-N2060WF2-12GD. Do however remember that not all registered graphics cards actually make it to market.

NVIDIA's revival of the RTX 2060 towards the current market conditions speaks in volumes. While NVIDIA is producing as many 8 nm cards as it can with foundry partner Samsung, the current state of the graphics card pricing market leaves no doubts as to how successfully NVIDIA has been able to cope with both the logistics and materials constraints currently experienced by the semiconductor market. The 12 nm manufacturing process certainly has more available capacity than Samsung's 8 nm; at the same time, the RTX 2060's mining capabilities have been overtaken by graphics cards from the Ampere family, meaning that miners most likely will not look at these as viable options for mining, thus improving availability for consumers as well. If the card does keep close to its expected $300 price-point upon release, of course.

Videocardz, citing their own sources in the industry, claims that NVIDIA is readying a resurrection of sorts for the popular RTX 2060 graphics card. One of the hallmarks of the raytracing era, the Turing-based RTX 2060 routinely stands as the second most popular graphics card on Steam's hardware survey. Considering the still-ongoing semiconductor shortages and overreaching demand stretching logistics and supply lines thin, NVIDIA would thus be looking at a slight specs bump (double the GDDR6 memory to 12 GB) as a marketing point for the revised RTX 2060. This would also add to the company's ability to deliver mainstream-performance graphics cards in a high enough volume that enables the company to keep reaping benefits from the current Ampere line-up's higher ASP (Average Selling Price) across the board.

Videocardz' sources claim the revised RTX 2060 will be making use of the PG116 board, recycling it from the original GTX 1660 Ti design it was born unto. Apparently, NVIDIA has already warned board partners that the final design and specifications might be ready at years' end, with a potential re-release for January 2021. While the increase to a 12 GB memory footprint on an RTX 2060 graphics card is debatable, NVIDIA has to have some marketing flair to add to such a release. Remember that the RTX 2060 was already given a second lease of life earlier this year as a stopgap solution towards getting more gaming-capable graphics cards on the market; NVIDIA had allegedly moved its RTX 2060 manufacturing allocation back to Ampere, but now it seems that we'll witness a doubling-down on the RTX 2060. Now we just have to wait for the secondary market pricing to come down from its current $500 average... For a $349 MSRP, 2019 graphics card.

Yesterday, we got information that Intel's upcoming DG2 discrete graphics card is "right around the corner". That means that we are inching closer to the launch of Intel's discrete GPU offerings, and we are going to get another major player in the current GPU market duopoly. Today, however, we are in luck because Igor from Igor's LAB has managed to get ahold of the specifications of Intel's Xe-HPG DG2 graphics card. For starters, it is important to note that DG2 GPU will first come to laptops later this year. More precisely, laptops powered by Alder Lake-P processors will get paired with DG2 discrete GPU in the second half of 2021. The CPU and GPU will connect using the PCIe 4.0 x12 link as shown in the diagram below, where the GPU is paired with the Tiger Lake-H processor. The GPU has its subsystem that handles the IO as well.

SK hynix Inc. today announced financial results for its first quarter 2021 ended on March 31, 2021. The consolidated revenue of the first quarter 2021 was 8.494 trillion won while the operating profit amounted to 1.324 trillion won, and the net income 993 billion won. Operating margin for the quarter was 16% and net margin was 12%.

The Company made better results both QoQ and YoY in the first quarter as the semiconductor market conditions improved earlier this year. Although the first quarter is usually off-season of the semiconductor industry, the Company said that the market conditions improved as demand for memory products for PCs and mobiles increased. In addition, cost competitiveness has increased as yields of major products have improved. Through this, the revenue and the operating profit increased by 7% and 37%, respectively, compared to the previous quarter.

The launch of NVIDIA's upcoming GeForce RTX 3080 Ti graphics card is upon us. The number of rumors circulating the web is getting greater and we have just received die pictures of the GA102 silicon and the specification of the specific SKU. Sources over at VideoCardz have provided the website with the first die picture of GA102-225 silicon, which powers the NVIDIA GeForce RTX 3080 Ti graphics card. Pictured below, it doesn't appear much different compared to the GA102-300 SKU found inside the RTX 3090 card, with the only obvious differentiator being the SKU ID. However, the difference only appears under the hood, with the GA102-225 SKU having 10240 CUDA cores instead of 10752 CUDA cores found inside GA102-300 of RTX 3090.

Paired with 12 GB of GDDR6X memory on a 384-bit bus, the memory will have run around 19 Gbps speeds. That will result in a bandwidth of 912 GB/s. If you are wondering about the performance of the card, it should remain within a few percent of its bigger brother RTX 3090. We have the first leak showing Ethereum mining performance and the GA102-225 silicon achieved a mining hash rate of 118.9 Mh/s with some tuning. The memory was overclocked to 21.5 Gbps, while the GPU TDP was limited to 278 Watts. The leak shows that the card has managed to achieve a 1365 MHz base and 1665 MHz boost frequency. While we don't have the exact launch date, the supposed MSRP will be anywhere from $999 to $1099, assuming you can get it at all at any price.

NVIDIA is slated to launch its performance-segment GeForce RTX 3060 "Ampere" graphics card on February 25, 2021, according to a WCCFTech report. The company launches the card at an MSRP (starting price) of USD $329. 12 GB is the standard memory size for the RTX 3060. The card marks the debut of the new 8 nm "GA106" silicon, NVIDIA's 4th chip based on the GeForce "Ampere" graphics architecture.

While the "GA106" silicon features up to 3,840 CUDA cores across 30 streaming multiprocessors, the RTX 3060 is reportedly being carved out by enabling 28 SM, working out to 3,584 CUDA cores. It features 12 GB of 15 Gbps GDDR6 memory across a 192-bit wide memory interface, which means 360 GB/s memory bandwidth, slightly higher than the 336 GB/s of the RTX 2060. The card has a typical board power rating of 170 W, which means plenty of custom-design graphics card models should come with single 8-pin PCIe power connector configurations. NVIDIA's design goal for the RTX 3060 could be doubling performance over the GTX 1060 "Pascal," and a significant performance uplift over the RTX 2060.

A well-known leaker from NVIDIA cards past, Kopite7Kimi, has launched a rumor wherein the previously "indefinitely postponed" RTX 3080 Ti graphics card might see the light of day as early as April. Designed as an NVIDIA response to the price/performance offering from AMD's RX 6900 XT graphics card, the RTX 3080 Ti with an overkill 20 GB GDDR6X was rumored to have been in the works following the AMD launch. However, inventory difficulties related not only to wafer production from Samsung, but also GDDR6X supply from Micron and delays in the logistics channels meant that NVIDIA chose to shelve this graphics card release.

The new, reinterpreted RTX 3080 Ti graphics card is rumored to axe the 20 GB of GDDR6X memory in favor of a more tenable 12 GB - which some might argue is but a slight, but sufficient improvement from the RTX 3080's 10 GB. That memory amount, however, means that the card will have to carry a different, wider, 384-bit memory bus, which should mean improved memory performance, but also increased board costs. The RTX 3080 Ti is now rumored as carrying 80 enabled Streaming Multiprocessors (12 more than the RTX 3080's 68, and 2 less than the fully-enabled chip present in the RTX 3090.

AMD is slowly preparing to launch its next-generation of mid-range graphics cards based on the RDNA 2 architecture. Following the launch of Navi 21 GPU SKUs, next in line comes the slower Navi 22 variant with fewer compute units (CU). Envisioned to compete against NVIDIA's GA104 and GA106 GPU SKUs, the Navi 22 based GPU is targeting 1440p gamers mainly. Today, thanks to Andreas Schilling from the German website HardwareLuxx, we got a few pieces of information regarding AMD's upcoming Radeon RX 6700 XT graphics card. The source is claiming that we are getting this card sometime in the first half of this year, with the possibility to get it in Q1.

The AMD Radeon RX 6700 XT graphics card is designed for 1440p gaming as mentioned, and its VRAM configuration is interesting. It features 12 GB of GDDR6 memory, which is more than enough for the types of workloads this card is meant for. The memory communicates using 192-bit bus. The Navi 22 GPU is configured for 40 CUs in total, with 2560 cores maximum. The Radeon RX 6700 XT features the Navi 22 XT variant with the fully enabled die, while its smaller brother Radeon RX 6700 is featuring Navi 22 XL die that has possibly fewer CUs and smaller TDP. The pricing of the upcoming cards is unknown.

It seems that Mini-ITX lovers will finally be able to get their due Ampere injection to their HPC or small form factor systems. MSI, Palit and Gainward have announced Mini-ITX versions of NVIDIA's RTX 3060 graphics card, enabling higher performance (especially in RTX workloads) than last generation's mainstream RTX 2060 graphics cards. MSI's Aero ITX will be available in base and OC variants, and there's currently no confirmation on how many power connectors are built into those cards (though a standard 8-pin would suffice).