PC enthusiasts who crave powerful graphics in compact systems have a new option from Zephyr. The Chinese manufacturer has launched the world's first ITX-sized GeForce RTX 4070 graphics card. Dubbed the Sakura Blizzard, this GPU packs NVIDIA's AD104-250 chip and 12 GB of GDDR6X memory into a footprint of just 172 x 123 x 42 mm. While slightly taller than standard PCIe brackets, the two-slot cooler should fit most Mini-ITX cases. The card's cute pink shroud and solitary cooling fan give it a unique aesthetic. But don't let the pink looks fool you - Zephyr claims this compact powerhouse can keep the GPU and memory up to 10°C cooler than some dual-fan RTX 4070 designs, which needs to be taken with a grain of salt. Thermal testing videos show the fan spinning at 2,400 RPM to maintain GPU temperatures around 73°C under load in a 25°C room. Meanwhile, synthetic benchmarks reportedly demonstrate no performance compromises versus full-sized RTX 4070 implementations.

Zephyr's initial production run has already sold out in China. However, a second batch is slated for mid-July availability to meet the apparent higher demand for small form factor RTX 40-series GPUs. The launch comes just weeks after NVIDIA unveiled new "SFF-ready" design guidelines at Computex 2024. As the power-hungry RTX 40 lineup hit the market, many voiced concerns over the cards' ever-growing dimensions. NVIDIA's renewed SFF PC focus signal options like the Sakura Blizzard could become more common. For space-constrained enthusiasts, having top-tier GPU muscle in a properly-cooled Mini-ITX card is a big win. Zephyr's ITX-sized RTX 4070 shows powerful things can come in small packages, and we hope more manufacturers follow this philosophy.

ASUS launched the Prime Series of GeForce RTX 40-series "Ada" graphics cards that meet NVIDIA's new SFF-Ready specification that sets 304 mm x 151 mm x 50 mm (length x height x thickness) as the maximum dimensions for a graphics card to qualify. What's interesting, is that NVIDIA intended for the SFF-Ready standard to apply to performance-segment and enthusiast-class GPUs (RTX 4070 SUPER and up), however, ASUS has designed the Prime series for the RTX 4060 Ti, RTX 4070, and RTX 4070 SUPER; there are no cards in the series based on the RTX 4070 Ti SUPER or the RTX 4080 SUPER, yet.

ASUS is using a common board design for its RTX 4070 SUPER, RTX 4070, and RTX 4060 Ti Prime series graphics cards, which measures 269 mm x 120 mm x 50 mm, while the heatsink and PCB underneath the cooler shroud may vary between the RTX 4070/SUPER and the RTX 4060 Ti cards. The cooler uses a trio of 70 mm fans to ventilate an aluminium fin-stack heatsink, much of the airflow from the third fan goes through the heatsink and back out from a large cutout in the backplate. The RTX 4070 and RTX 4060 Ti cards use single 8-pin PCIe power inputs, while the RTX 4070 SUPER uses a 16-pin 12VHPWR input. There are a total of six SKUs, two per GPU, one of which sticks to the NVIDIA reference clock speeds, and the other being an OC SKU with a minor factory overclock.

Graphics card enthusiasts with a thing for earthy green hues, will likely appreciate Manli's latest products—its Gallardo graphics card range has expanded with two new models. The Asian and European market-focused manufacturer has already unleashed "refreshed" models that utilize NVIDIA's GeForce RTX 40-series SUPER GPUs, but the newest entries sport a revised signature green flagship "Gallardo" design. VideoCardz has pored over the small details—it turns out that Manli has produced a slimmer profile: "perhaps something that is not obvious is that Manli has introduced the RTX 4070 Ti SUPER Gallardo already. The new version marks a second revision, featuring an entirely different aesthetic compared to its predecessor. The most important change is that it no longer occupies a 3.5-slot space." Manli has evidently put together a "much slimmer 2-slot version" under a "M3604+N693" moniker.

The non-Ti model is likely coming out soon, but Manli has not yet announced official pricing or launch date details for their newly redesigned Gallardo Ada Lovelace cards—official product pages were created last week. Despite flagship status, VideoCardz notes that Manli has not implemented any factory overclocking—the Gallardo range is often associated with: "system integrators like Sycom for further customization." The spec sheet advertises integrated LED lighting with seven available color cycles, four 6 mm copper heat pipes with segmented heatsinks, and a metal backplate for reinforcement and protective purposes.

NVIDIA completed its last round of GeForce NVIDIA RTX 40-series GPU refreshes at the very end of January—new evidence suggests that another wave is scheduled for imminent release. MEGAsizeGPU has acquired and shared a tabulated list of new Ada Lovelace GPU variants—the trusted leaker's post presents a timetable that was supposed to kick off within the second half of this month. First up is the GeForce RTX 4070 GPU, with a current designation of AD104-251—the leaked table suggests that a new variant, AD103-175-KX, is due very soon (or overdue). Wccftech pointed out that the new ID was previously linked to NVIDIA's GeForce RTX 4070 SUPER SKU. Moving into April, next up is the GeForce RTX 4060 Ti—jumping from the current AD106-351 die to a new unit; AD104-150-KX. The third adjustment (allegedly) affects the GeForce RTX 4060—going from AD107-400 to AD106-255, also timetabled for next month. MEGAsizeGPU reckons that Team Green will be swapping chips, but not rolling out broadly adjusted specifications—a best case scenario could include higher CUDA, RT, and Tensor core counts. According to VideoCardz, the new die designations have popped up in freshly released official driver notes—it is inferred that the variants are getting an "under the radar" launch treatment.

Seasonic introduced a new 12V-2x6 modular PSU cable model late last year—at the time, interested parties were also invited to Beta test early examples. Finalized versions have been introduced, via a freshly uploaded YouTube video (see below) and a dedicated product page. The "H++" connector standard—part of a new ATX 3.1 specification—is expected to replace the troubled "H+" 12VHWPR design. The PC hardware community has engaged in long-running debates about the development and rollout of a danger/peril-free alternative. PCI-SIG drafted the 12V-2x6 design last summer.

Seasonic's introductory section stated: "with the arrival of the new ATX 3 / PCIe 5.0 specifications, some graphic cards will now be powered by the new 12V-2x6 connector. Offering up to 600 W of power, the Seasonic native 12V-2x6 cable has been crafted with high quality materials, such as high current terminal connectors and 16 AWG wires to ensure the highest performance and safety in usage." The new cables are compatible with Seasonic's current ATX 3.0 power supply unit range—including "PRIME TX, PRIME PX, VERTEX GX, PX, GX White and Sakura, FOCUS GX and GX White" models. Owners of older Seasonic ATX 2.0 PSUs are best served with an optional 2x8-pin to 12V-2x6 adapter cable—although 650 W rated and single PCIe connector-equipped units are not supported at all. Two native cable models, and a non-native variant are advertised in the manufacturer's video.

MAINGEAR, the leader in premium-quality, high-performance gaming PCs, announces its 2024 preconfigured MG-1 gaming PCs, featuring the latest NVIDIA GeForce RTX 40-Series SUPER GPUs. Designed to redefine the gaming experience, these newly announced pre-configured systems, starting at $1,199, offer enhanced performance, diverse options, more memory, larger SSD capacities, and can be had with Windows 11 Pro.

"Refreshing the MG-1 Series to feature the latest gaming hardware and components represents our ongoing commitment to delivering cutting-edge gaming experiences. With the latest Intel & AMD processors, NVIDIA GPUs, including the new SUPERs, and a broader range of options in the MG-1, MAINGEAR continues to set the standard for gaming excellence." - Wallace Santos, CEO of MAINGEAR.

NVIDIA today launched the third and final high-end GPU in its GeForce RTX 40-series SUPER refresh. The new GeForce RTX 4080 SUPER is being launched at an attractive $999 price, compared to the $1,199 that the RTX 4080 originally launched at. Besides this huge 20% cut in pricing, there's also more performance on offer, as the company chose to max out the 5 nm AD103 silicon that it's based on. If you recall, the RTX 4080 has 76 out of 80 streaming multiprocessors of the AD103 enabled, and its memory runs at an odd 22.4 Gbps speed. The RTX 4080 SUPER gets all 80 SM, and a well rounded 23 Gbps memory speed.

With 80 SM on tap, you get 10,240 CUDA cores, 320 Tensor cores, 80 RT cores, 320 TMUs, and 112 ROPs. The memory size is unchanged at 16 GB, across the 256-bit wide memory interface of the AD103; as is the total graphics power (TGP), at 320 W. All cards will include an NVIDIA-designed adapter that converts three 8-pin PCIe power connectors into a 12VHPWR that's capable of delivering 450 W of power. The target audience for this card is the same as that of the RTX 4080—maxed out 4K Ultra HD gaming with ray tracing. At $999, the RTX 4080 SUPER allows NVIDIA to better compete with the AMD Radeon RX 7900 XTX that's sometimes spotted for prices as low as $900. Don't forget to catch our exhaustive review coverage from the links below!

NVIDIA GeForce RTX 4080 SUPER Founders Edition | ASUS ROG Strix RTX 4080 SUPER OC | ASUS TUF Gaming RTX 4080 SUPER OC | MSI RTX 4080 SUPER Expert | Gigabyte RTX 4080 SUPER Gaming OC | PNY RTX 4080 SUPER Verto | Galax RTX 4080 SUPER SG 1-click OC | Palit RTX 4080 SUPER GamingPro OC | Zotac RTX 4080 SUPER AMP Extreme AIRO

GIGABYTE has augmented its EAGLE range of custom graphics card with a new white "ICE" design—the Taiwanese hardware manufacturer's website has been updated with four GeForce RTX 40 Series models that sport a striking white aesthetic. The modern day EAGLE custom cooling solutions usually pops up in a sober yet classy gray shade (with some lighter accents)—it seems that alternatives, ideal for all-white hardware build, will be arriving soon. GIGABYTE has not revealed any information regarding regional pricing, release date or a press release (at the time of writing). Four factory overclocked EAGLE ICE models are listed—starting at the bottom with a pale version of their existing RTX 4060 EAGLE OC 8 GB card, and reaching the ceiling with a white spin on their RTX 4070 Ti SUPER EAGLE OC 16 GB.

GIGABYTE has chosen to not produce an EAGLE graphics card that utilizes NVIDIA's GeForce RTX 4080 SUPER GPU, so an ICE version is unlikely to pop up in the immediate future. GIGABYTE's RTX 4080 SUPER AERO OC model seems to be the only option available in white—within their current (Ada Lovelace) AD103-400-A1 GPU product range. VideoCardz reckons that there is a high probability of EAGLE ICE (non-overclocked) graphics cards arriving after the initial launch of OC models.

According to the recent listing on Goofish, discovered by VideoCardz, Chinese companies have begun selling mobile versions of NVIDIA's latest RTX 40-series GPUs as desktop graphics cards. Initially designed for gaming laptops, the GeForce RTX 4080M and RTX 4090M are now being marketed in China as more affordable alternatives to their official desktop counterparts. This development is no surprise to industry observers who recall similar adaptations with the RTX 20 and 30 series. These companies are leveraging the lower cost of mobile GPUs, combined with budget cooling solutions and simpler PCB designs, to offer more affordable desktop GPU options. The mobile GPUs, which are capped at a power consumption of 175 Watts, are being repurposed without official sanction, with NVIDIA seemingly disregarding this practice. Despite the lack of official endorsement, these modified GPUs are finding their way into the market, providing gamers a cost-effective alternative to the more expensive desktop versions.

While not officially supported by NVIDIA, these cards utilize the mobile GPU dies paired with custom cooling solutions and PCBs to work in desktop PCs. According to reports, the RTX 4080M desktop variant offers 7424 CUDA cores and 12 GB GDDR6 memory, representing a 24% reduction in cores and 4 GB less memory versus the desktop RTX 4080. The desktop RTX 4090M is even more cut-down, with 9728 cores and 16 GB memory—a 40% drop in cores and 8 GB less memory than the flagship RTX 4090 desktop card. Pricing falls between $420 and $560 for the RTX 4080M and exceeds that of even the desktop RTX 4090 for the 4090M variant. Performance and longevity still need to be determined for these unofficial cards. While they present a cheaper RTX 40-series option for Chinese gamers, the reduced specifications come with tradeoffs. Still, their availability indicates the ongoing demand for next-gen GPUs and the lengths some vendors go to to meet that demand.

Market research by Korean publication Danawa DPG provides valuable insights to how desktop AMD Ryzen processor users are charting their upgrade paths given the long upgrade longevity of AMD sockets. The research follows a 10-month date range from December 2022 to October 2023, and tracks the sales of motherboards based on various AMD chipset models. We're shown that toward the turn of the year, AMD B550 chipset motherboards sell the most. This is when AMD Ryzen 5000 Socket AM4 processors top sales for the company, Given that the B550 fully supports CPU overclocking, and that there are plenty of feature-packed B550 motherboard models, it explains why the B550 covers a wide price-band.

AMD launched the Ryzen 7000 series "Zen 4" to lukewarm response in September 2022, mainly because the platform lacked DDR4 memory support that was relevant at the time, and hence wasn't as flexible to consumers as Intel's LGA1700. Its launch caused price-cuts for Ryzen 5000 series processors, clearing out some upgrade headroom for those on the AM4 platform still using Ryzen 3000. Off to a slow start, we see its successor from Socket AM5, the B650 chipset, rise steadily over the time period, and for two reasons—DDR5 memory became affordable over the course of 2023; and AMD breathed life into the Ryzen 7000 series with the introduction of the Ryzen 7000X3D series, which restored gaming performance competitiveness to Intel's 13th Gen Core "Raptor Lake." The B650 has everything you need right now for a Ryzen 7000X3D build, given that both the GeForce RTX 40-series and Radeon RX 7000 series are PCIe Gen 4 graphics cards; and that the B650 has at least a Gen 5 NVMe slot. If you absolutely need a Gen 5 x16 slot, there's the premium B650E chipset to go with.

The NVIDIA GeForce RTX 40-series SUPER lineup is real, and is coming this January, Chinese tech site IT Home reports. The publication released the exact dates on which NVIDIA is announcing the series, along with their market availability dates. The lineup refreshes the higher end of the RTX 40-series, and consists of three SKUs—the GeForce RTX 4080 SUPER, the GeForce RTX 4070 Ti SUPER, and the GeForce RTX 4070 SUPER.

According to the IT Home report, NVIDIA in a GeForce RTX event along the sidelines of the 2024 International CES, will announce all three SKUs on January 8. This will be followed by a January 17 release for the GeForce RTX 4070 SUPER. This is when you'll be able to buy the card. A week later on January 24, the company will make the GeForce RTX 4070 Ti SUPER available. Wrapping things up will be the January 31 availability of the GeForce RTX 4080 SUPER.

Akasa introduced a couple of new accessories designed to solve the problem of an obtuse cable bend of the 16-pin 12VHPWR power cable that compounds the problem of tall high-end graphics cards not getting along well with some of the more compact PC cases—of which Akasa specializes in. These include the G-Nexus P24, and G-Nexus PX24. The G-Nexus P24 is a solid-state L-shaped adapter and connector converter. One of its sides has three 8-pin PCIe power connectors, which it converts to a 12VPWR on the other end, at a 90° angle. This 12VHPWR is rated for 450 W, which should cover all RTX 40-series graphics cards up to the RTX 4080. It might be possible to even pair this with an RTX 4090, though the 450 W connector power limit could take the edge off overclocked performance. All custom RTX 4090 cards include a 600 W-rated adapter cable (that demand four 8-pin PCIe inputs).

The Akasa G-Nexus PX24 is a slightly different take on this concept, with a 30 cm cable between the 12VHPWR (which is held at a 90° angle), and the other end that has the three 8-pin PCIe inputs, arranged next to each other on a single piece. It's important to note here, that while Akasa is converting three 8-pin PCIe (3x 150 W) to a 12VHPWR on both accessories, the connector has its signal pins set to tell the graphics card that it is capable of delivering 600 W. This would obviously mean that any continuous load above 450 W would go above the 150 W specification limit of the PCIe connectors. The company didn't reveal pricing.

NVIDIA today announced the important milestone of 500 games and apps that take advantage of NVIDIA RTX, the transformative set of gaming graphics technologies, that among many other things, mainstreamed real-time ray tracing in the consumer gaming space, and debuted the most profound gaming technology of recent times—DLSS, or performance uplifts through high-quality upscaling technologies. The company got to this milestone over a 5-year period, with RTX seeing the light of the day in August 2018. NVIDIA RTX is the combined feature-set of real time ray tracing, including NVIDIA-specific enhancements; and DLSS.

Although it started out as an upscaling-based performance enhancement that leverages AI, DLSS encompasses a whole suite of technologies aimed at enhancing performance at minimal quality loss, and in some cases even enhances the image quality over native resolution. This includes super resolution, or the classic DLSS and DLSS 2 feature set; DLSS 3 Frame Generation, which nearly doubles frame-rates by generating entire alternate frames entirely using AI, without involving the graphics rendering machinery; and DLSS 3.5 Ray Reconstruction, which attempts to vastly improve the fidelity of ray traced elements in upscaled scenarios.

More performance for RTX 4070Ti and RTX 4090 GPUs! With this new and innovative cooler, Alphacool is expanding its range to include active water cooling for NVIDIA RTX 4070 Ti and RTX 4090 graphics cards. Thanks to the particularly delicate fin structure, the cooling surface has been enlarged and a high water flow rate has been realized. The jet plate with revised inflow also distributes the water optimally over the cooling fins. The enormous waste heat from the new generation of graphics cards is thus excellently dissipated by the cooler. The full-surface chrome plating of the copper base not only offers resistant protection against acids, scratches and damage, but also achieves a beautiful homogeneity and a special shine.

The Aurora design is visually calm and simple, as only one O-ring runs around the entire radiator. The design of the cooling fins and the jetplate also ensures a clear look. Thanks to the chrome plating, the illumination using digitally addressable RGB LEDs spreads evenly throughout the cooler. The Core GeForce RTX 4090 Master V.2 is now available for pre-order in the Alphacool store. The Eisblock Aurora GeForce RTX 4090 Aorus Master - Gaming V.2 and the Eisblock Aurora GeForce RTX 4070 TI ROG Strix are now available for delivery in the Alphacool online store.

NVIDIA is rumored to be working on a refresh of the higher end of its GeForce RTX 40-series "Ada" series, according to hongxing2020, a reliable source with NVIDIA leaks. The company could be bringing back the SUPER brand extension that it introduced with the RTX 20-series. As many as three SKUs are on the radar—GeForce RTX 4080 SUPER, GeForce RTX 4070 Ti SUPER, and the GeForce RTX 4070 SUPER.

There is no word on when the company plans to release these, or what their specifications are, but we can certainly speculate. The current RTX 4080, while based on the AD103 silicon, doesn't max it out—it uses 76 out of 80 SM (streaming multiprocessors) available on the silicon, but we doubt if those extra 4 SM could drive up enough performance to make a whole new SKU, especially given that the 256-bit memory bus of the AD103 is maxed out. We predict that the RTX 4080 SUPER could be based on the larger AD102 silicon that physically has 144 SM that the current RTX 4090 uses 128 out of. NVIDIA has the opportunity to pick an SM count such as, say, 96. AD102 also has a wider 384-bit memory bus, giving NVIDIA the option of either giving the RTX 4080 SUPER the same 24 GB memory configuration as the RTX 4090, or even 20 GB, across a 320-bit memory bus.

NVIDIA today released the latest version of its GeForce graphics drivers. The company released the GeForce 545 series drivers, a huge jump in version numbering from the GeForce 537 series. The new drivers extend NVIDIA RTX Video Super Resolution 1.5 technology down to even RTX 20-series "Turing" GPUs, besides the current RTX 30-series "Ampere" and RTX 40-series "Ada." The technology is a high-quality video upscaler that uses some of the upscaling techniques borrowed from DLSS feature-set over to video. The drivers also add optimization for the latest "Naraka: Bladepoint" patch that introduces DLSS 3 Frame Generation, as well as "Warhammer Vermintide II" DLSS 3 update. The drivers add TensorRT acceleration for Stable Diffusion. The drivers also add GeForce Experience optimal settings for over a dozen game titles. Among the issues fixed include a random black screen flicker seen on displays that use DSC (display stream compression), and incorrect monitor colors when returning from display sleep.

DOWNLOAD: NVIDIA GeForce 545.84 WHQL

NVIDIA today released the GeForce 537.42 WHQL Game Ready drivers. These introduce support for the new DLSS 3.5 Ray Reconstruction technology, which will work on all GeForce RTX GPUs, including RTX 20-series "Turing," RTX 30-series "Ampere," and the latest RTX 40-series "Ada." Ray Reconstruction is a data-driven DNN-based ray tracing denoiser that produces superior results than hand-tuned legacy denoisers. In particular, ray traced elements such as shadows and reflections in games that use DLSS 2 (super resolution), should look more natural. The driver also comes with optimization for "Cyberpunk 2077: Phantom Liberty," besides "Warhaven," "Witchfire," and "Party Animals." The drivers also fix a couple of performance issues with Octane Renderer.

DOWNLOAD: NVIDIA GeForce 537.42 WHQL

Be sure to check out our Performance and Image Comparison review of DLSS 3.5 Ray Reconstruction later today, and our technical overview of how it works.

Chinese board partner Maxsun introduced its flagship—Mega Gamer GPU (MGG)—GeForce RTX 40-series lineup earlier this year, debuting with an RTX 4070 Ti card, and then an RTX 4080 MGG OC 16G model. The rather unique looking cooling solution attracted some attention at the time—a traditional set of three 100 mm fans was augmented with two additional 40 mm "Air Burst" units in a flanking position, acting as exhausts as for the finstack. Earlier today Maxsun revealed the range topping RTX 4090 MGG OC 24G model via a video uploaded to their Weibo channel.

The new headliner looks to be fitted with the same shroud design as seen on the already released RTX 4080 MGG OC 16G model, which includes a somewhat gimmicky magnetically detachable large top-facing RGB LED panel, dubbed "MGG LED Ambient Kit." Thankfully Maxsun has put the work into creating a robust cooling solution, with a vapor chamber capable of meting out 7000 mm² of heat dissipation. Their GeForce RTX 4090 MGG OC 24G model's TDP has been rated at 450 W TDP, with a factory overclock providing a 2580 MHz boost clock. As reported by VideoCardz, Maxsun seems to be sticking to a Chinese market launch for the moment—the company's international AliExpress store has not been updated with a listing for the range topping Mega Gamer GPU.

ASUS is readying a wider range of Evangelion-themed ROG product line, building on the collaboration the company built with the popular Japanese action anime in 2022. The 2023 lineup is comprehensive, and includes a special Evangelion edition of the ROG Maximus Z790 Hero motherboard, special edition variants of GeForce RTX 40-series ROG Strix graphics cards (could be anything from the RTX 4070 thru RTX 4090), a special edition ROG Hyperion GR701 case, themed ROG Ryujin II AIO CPU cooler, a themed ROG Thor ATX 3.0 power supply, and lastly, keycap and body panel sets for its various ROG gaming peripherals. ASUS is planning to showcase the 2023 Evangelion lineup at Bilibili World, later this month.

A recent report published by BoardChannels points to Galax possibly implementing a broad set of price cuts across its range of NVIDIA GeForce RTX 40 and 30-series custom graphics card models. Insider information originating from sources within a pool of NVIDIA and AMD board partners suggests that Galax could be shaving off up to 1000 RMB (around $140) from certain Ampere and Ada Lovelace products - effective later this month in its native Hong Kong market as well as mainland China.

The article posits that GeForce RTX 4080 cards could end up becoming 1000 RMB cheaper, and popular RTX 3060 models receiving cuts of around 250 RMB (≈$35). Galax is reported to have already offered entry-level desktop GeForce RTX 3050 cards at lower prices in the latter half of May - with 140 RMB (≈$19.50) reductions. The RTX 4070 series is supposedly set to receive a measly discount of around 150 to 200 RMB (≈$21 to $28), which is likely not doing it many favors given slow worldwide uptake since the product range's launch in mid-April. Galax could be making adjustments to fall in line with rivals (in the region) who have already reduced asking prices for NVIDIA gaming hardware.