Hot on the heels of rumored specs of the GeForce RTX 5070 SUPER and RTX 5070 Ti SUPER, rumored specs of the RTX 5080 SUPER emerged on VideoCardz. Apparently, NVIDIA will not tap into the larger "GB202" silicon to build the RTX 5080 SUPER despite maxing out the "GB203" silicon to build the current RTX 5080. It will take a slightly different approach, by giving the card additional memory and power limits. 24 Gbit GDDR7 memory chips are a distinct feature of RTX 50-series SUPER graphics cards, and much like the RTX 5070 Ti SUPER, the RTX 5080 SUPER will feature 24 GB of GDDR7 memory across a 256-bit wide memory bus.

NVIDIA could possibly use 30 Gbps memory speeds for this SKU to end up with at least the same kind of bandwidth as the regular RTX 5080, which is 960 GB/s. The other interesting aspect of the RTX 5080 SUPER is expected to be its increased TGP (total graphics power) value of 415 W, a 15% increase over the 360 W TGP of the RTX 5080. This increase in TGP will not just support the higher density memory chips, but also allow NVIDIA to increase GPU clock speeds. This will likely be necessary, given that NVIDIA has no headroom to increase shader counts on "GB203," and will need something to increase performance for games without heavy memory demands.

We have already covered that NVIDIA is planning a SUPER refresh of its GeForce RTX 50 series GPUs, with the most recent leak revealing the GeForce RTX 5070 SUPER, which is expected to feature a slight increase in CUDA core count and 18 GB of memory. However, NVIDIA is also overhauling its RTX 5070 Ti with the SUPER treatment, now enabling the RTX 5070 Ti SUPER to feature as much as 24 GB of GDDR7 memory with no change in CUDA core count. According to kopite7kimi, the RTX 5070 Ti SUPER will feature the same 8,960 CUDA core configuration as the GB203-350-A1 SKU, based on the PG147-SKU55 PCB. The only difference here is the VRAM surplus resulting from an additional 8 GB of GDDR7, which totals 24 GB capacity, compared to the 16 GB now on the regular RTX 5070 Ti SKU.

This also changes the TBP of the card, where the RTX 5070 Ti SUPER GPU is now rumored to feature a 350 W TBP, an upgrade from the non-SUPER's RTX 5070 Ti, which has a 300 W power rating. Perhaps the extra power is dedicated now not only to more VRAM (which is also a power consumer) but to higher clock speeds, too. It wouldn't be sufficient to call it a SUPER variant without some raw compute increase, so NVIDIA might be selecting better die bins for the SUPER SKU to enable higher default clock speeds at only a 50 W TBP increase. Nonetheless, we expect to hear more details in the coming weeks, especially since the wave of rumors has started to flood social media and leaks are becoming more frequent.

G.SKILL International Enterprise Co., Ltd., the world's leading brand of performance overclock memory and PC components, is pleased to announce that CENS from Germany has once again claimed the title of OC Champion and the grand cash prize of $10,000 USD in the OC World Cup 2025 extreme overclock competition held live at Computex 2025. After an intense series of extreme overclocking challenges, CENS emerged victorious, demonstrating unmatched overclocking knowledge and technical skill with liquid nitrogen cooling, using the latest Intel Core Ultra 9 285K processor and ASUS ROG Maximus Z890 Apex motherboard. This is his second consecutive OC Champion title, after his victory last year at the OC World Cup 2024.

Exhilarating Competition with G.SKILL DDR5 24 GB Modules
This year at the live competition, the contestants are only allowed to use G.SKILL's high-performance 24 GB DDR5 module. It gave the contestants a new challenge to explore the 24 GB module's overclocking behavior and benchmarking potential. These 24 GB modules, built with SK hynix ICs, showcased exceptional headroom on Intel Z890 chipset platforms, allowing CENS to achieve up to DDR5-10266 CL32 2x24GB for benchmarking under LN2 cooling. At the same time, Seby, a rival overclocker contestant in the G.SKILL OC World Cup 2025, achieved DDR5-12666, which was the fastest memory frequency validation throughout the live competition.

With Computex 2025 in full swing, we learn that NVIDIA's next "SUPER" refresh may soon arrive: reliable leaker kopite7kimi has dropped fresh rumors surrounding the upcoming GeForce RTX 5080 SUPER. In a recent post on X, the leaker indicated that this new card will continue to use the GB203 GPU, matching the existing RTX 5080's full capacity of 10,752 CUDA cores. The only SUPER improvement lies in memory capacity and speed. Unlike the base model's 16 GB of GDDR7 running at 30 Gbps, the SUPER variant features 24 GB of GDDR7 at 32 Gbps, giving it a 1 TB/s of theoretical bandwidth. This increase in VRAM could yield noticeable benefits in high-resolution gaming and professional workloads that demand extensive frame buffers. Early bandwidth estimates suggest a 6% uplift in throughput when compared to the standard RTX 5080's 960 GB/s.

At the same time, the higher memory density requires denser 3 GB modules, similar to those already used in the RTX PRO 6000. Power requirements will rise accordingly. The SUPER model is rumored to draw over 400 W, about 40 W more than the vanilla RTX 5080's 360 W rating. Now, only NVIDIA's flagship RTX 5090—with 21,760 cores and 32 GB of GDDR7 across a 512‑bit bus—will exceed the 5080 SUPER in both compute and memory resources, not counting the last-generation top-tier RTX 4090. The exact launch date remains unconfirmed. While earlier rumors pointed to a Q4 2025 release, a new schedule could see NVIDIA debut the new card by early 2026 at a major trade show such as CES. Pricing is equally speculative. A possible MSRP target would be between $1,000 and $1,500, and it would be positioned to avoid direct competition with NVIDIA's entry‑level professional Blackwell GPUs. As always, until official announcements are made, specifications and launch windows should be taken with a grain of salt.

Late last week, Intel's social media account dropped a major hint about a new family of Arc Pro GPUs turning up at Computex 2025. At the time, insiders shared very basic details about a rumored "B60" workstation graphics card—likely derived from familiar Xe2 "Battlemage" silicon. Team Blue staffers have recently teased a mysterious "B770" gaming solution, but this "higher -end" desktop option could emerge well after next week's important trade show (in Taipei, Taiwan). Intel and its board partners seem to be readying productivity-focused cards; theoretically spun-off from the existing B580 12 GB model.

April/May leaks have indicated pairings of Team Blue's "BMG-G21" GPU die and 24 GB of GDDR6 VRAM. On Monday, industry observers noted the very fresh registration of Maxsun Arc B580 "iCraft 24G" and "iCraft 24G OC" SKUs. Days later, VideoCardz has stumbled upon evidence of an "Arc Pro B60" product category. At the time of writing, this entry remains empty—within the manufacturer's "Intel" card inventory. Active "Arc B580" and "Arc B570" categories direct you to already launched (12 GB) iCraft and Milestone models. According to slightly older reports, Maxsun is expected to introduce/launch "gaming" Arc B580 24 GB variants at some point after Computex 2025. The immediate focus—for Intel and participating AIBs—seems to be an imminent unveiling of "Arc Pro B-series" cards.

Around late April, Chinese industry insiders started whispering about a possible halting of NVIDIA GB202 "Blackwell" GPU shipments into the region. Team Green's local board partners released custom "market exclusive" GeForce RTX 5090D 32 GB cards; featuring slightly downgraded flagship silicon. Since launch, Chinese hardcore gaming enthusiasts and DIY AI firms have observed impressive performance credentials, despite the presence of factory limited specifications. On May 6, reports suggested a complete halt of GeForce RTX 5090D sales in China. Fresher rumors indicate NVIDIA's engineering team return to the drawing board; with their alleged preparation of an even weaker GeForce RTX 5090D design.

A group of Baidu tipsters have discussed a key area of (further) compromise: VRAM capacity. The original GeForce RTX 5090D configuration was armed with 32 GB of GDDR7 VRAM; mid-May speculation envisioned a 24 GB variant. Earlier today, harukaze5719 highlighted an intriguing Weibo post. A Manli webshop representative has "confirmed" that revised GeForce RTX 5090D cards will become available around July. Up until recent events, this Chinese brand was selling flagship GPU-based Gallardo (black) and Stellar (white) models. A web chat session was captured and shared on Weibo—in addition, the sales agent disclosed their belief that (NVIDIA's) supply of GeForce RTX 5090D GPUs has been "insufficient since launch" time. On a semi-positive note, customers will not be greeted by price hikes. Manli anticipates "unchanged" price tags; albeit associated with lesser specifications.

NVIDIA's rollout of "Blackwell" generation GPUs is not complete, as rumors of a mid‑cycle refresh are already gaining momentum. Latest rumors point to a GeForce RTX 5080 SUPER (or "Ti," depending on what NVIDIA calls it) could arrive before the year is out, aiming to fill the gap between the base RTX 5080 and the flagship RTX 5090. Right now, the standard RTX 5080 comes with 16 GB of GDDR7 memory, while the RTX 5090 doubles that to 32 GB. According to a tipster on Baidu, the SUPER/Ti model would slot in at 24 GB, giving memory‑hungry games and applications a boost without stepping on the 5090's toes. Beyond that bump in RAM, though, we're still in the dark about core counts, clock speeds, and power targets.

On a related front, the China‑only RTX 5090D is reportedly being overhauled because of new US export restrictions. The revamped 5090D is said to lose almost a third of its shader hardware, dropping from 21,760 cores down to 14,080, similar to the professional‑grade RTX Pro 5000. Even if NVIDIA cranks up the clock speeds, that cut in cores would almost certainly drag performance back toward last‑generation RTX 4090 levels. Memory architecture might take a hit too: the revised 5090D could shift from a 512‑bit bus to 384 bits, reducing bandwidth by 25% even while keeping 32 GB of GDDR7. Some leaks even suggest NVIDIA might trim its VRAM to 24 GB, which would oddly line it up with the rumored spec for the upcoming 5080 SUPER.

Maxsun's parent company has quietly registered new 24 GB versions of Intel's Arc B580 graphics card with the EEC. While regulatory filings often cover placeholder or speculative hardware, this submission lines up with ongoing rumors about a high-memory "Battlemage" model aimed at both gamers and professionals. Back in December and January, Intel launched the Arc B580 and B570 GPUs, bringing the Battlemage architecture to desktops just a few months after "Lunar Lake" appeared on laptops. Those first cards came with 12 GB of GDDR6 memory, a surprisingly generous amount for graphics cards selling under $300, and they helped establish Intel as a real contender in the mainstream GPU market. Since then, chatter about a 24 GB version has never died down. The story gained weight when board partner Sparkle briefly hinted at such a variant and then retracted the comment under NDA obligations. Further fueling speculation, a Sparkle representative in China discussed the planned "B580 24 GB" during a March social-media exchange.

Now, Maxsun's EEC filing lists two models called "iCraft 24G" and "iCraft 24G OC," and those names match what Sparkle first mentioned. There's no guarantee these cards will actually hit store shelves, but the matching details and timing suggest Intel may be testing the waters for a memory-heavy Arc B580. That would make sense given recent leaks about an Arc PRO A60 workstation card also packing 24 GB of memory. Under the hood, the Arc B580's BMG-G21 chip offers up to 20 Xe cores and 2,560 shader units, putting it in the same ballpark as NVIDIA's GeForce RTX 4060. With Computex just days away, Intel will finally reveal whether these high-memory Arc B580 cards, or perhaps even bigger Battlemage-based workstation GPUs, are coming our way. Additionally, enthusiasts are keeping an eye on the rumored Arc B770, which is expected next quarter and likely to be detailed at Computex alongside Intel's broader Battlemage and upcoming Xe3 "Celestial" roadmap.

Earlier in the week, reports indicated the potential introduction of an Intel Xe2 "Battlemage" B770 gaming graphics card at Computex 2025. Last night, a Team Blue tweet confirmed forthcoming product unveilings: "new Intel Arc Pro GPUs are on the way. See you in Taipei!" In the months leading up to this important trade event, industry watchdogs have drummed up speculation about "Battlemage's" future (or fate). Whispers of 24 GB VRAM-equipped variants emerged late last year—around late January, these theories were connected to an official leak: "3 new PCI IDs for BMG."

Unsurprisingly, VideoCardz has weighed in with some new inside track info—they propose that one of Intel's upcoming professional options will be an "Arc Pro B60 24 GB" model, aka "Developer Edition" (an alleged in-house reference). Despite Sparkle HQ downplaying recent "rogue claims," a company rep (in China) alluded to a possible May/June release of their own custom 24 GB "Battlemage" productivity-oriented card. VideoCardz has picked up on rumors, regarding the "Arc Pro B60's" internal setup. They propose Team Blue's selection of the familiar "BMG-G21" GPU; as used by their Arc Xe2 B580 12 GB and B570 10 GB designs. According to an unnamed inside source, this professional/workstation variant will stick with the usual 192-bit memory interface. Intel's Computex 2025 new product teaser provided a big clue about the speculated "B60" model's cooling solution.

Intel has only released two Arc Xe2 "Battlemage" desktop models: the B580 12 GB and B570 10 GB graphics cards. So far, these lower priced options have been warmly welcomed by reviewers and buyers alike—but gaming GPU enthusiasts are still actively clamoring for more potent second-gen "Battlemage" variants. The collective status of theorized "B750, B770, and (fancifully) B780" SKUs is frustratingly unclear. Intel has not generated any official new product noise since the launch of their B570 design, earlier this year—recent big announcements have focused on next-gen "AI PC" processor lines. A series of vague leaks have indicated cancelations and then revivals of speculated mid-to-high-end Arc Xe2 discrete cards.

As of late, a larger "BMG-G31" GPU identifier has appeared in shipping manifests—a previous leak pointed to "prototype" units being moved between company facilities. Yesterday, Haze2K1 shared another extract from NBD inventory documents—crucially, they believe that these items are heading to a crucial manufacturing plant in Vietnam. This location is/was tasked with the assembling of first-party B570 and B580 Limited Edition products. Fresh conjecture suggests that "B7XX" Limited Edition cards are in the pipeline, but current circumstances are still hazy. VideoCardz reckons that a "Developer Edition" 24 GB model is still in active development, but this rumored workstation/productivity-oriented card could be based on Intel's readily available "BMG-G21" GPU die.

NVIDIA has significantly advanced professional graphics by rebranding its workstation lineup as "RTX PRO" and incorporating an amazing 96 GB of GDDR7 memory capacity into a single RTX PRO 6000 card. This marks the first time 3 GB GDDR7 modules have been employed in a workstation GPU, each supporting error-correcting code for enhanced reliability. By arranging 16 such modules on each side of the PCB, NVIDIA achieves the remarkable 96 GB capacity while maintaining a TDP limit of 300 W for its Max-Q variant (pictured below) and up to 600 W for other SKUs. A recent leak on the Chiphell forum provides a clear insight into the new PCB layout. The customary 12 V-6×2 power connector has been omitted and replaced by four solder points intended for a cable extension.

This design choice suggests preparation for both Server and Max-Q editions, where power inputs are relocated to the rear of the card. Despite the simplified power interface and reduced footprint, the Max-Q model retains the full GB202 Blackwell GPU and the complete memory capacity. At the top of the series, the RTX PRO 6000 Blackwell will be offered in three distinct configurations. The Workstation and Server editions feature 24,064 CUDA cores, 96 GB of GDDR7 ECC memory, and a 600 W power budget, ensuring consistent performance in desktop towers and rack-mounted systems. The Max-Q edition employs the identical GPU and memory configuration but limits power consumption to 300 W through lower clocks and power limits, making it particularly well suited for compact chassis and noise-sensitive environments.

Mere months after the launch of GeForce RTX 5080 16 GB and RTX 5070 12 GB graphics cards, industry rumors are already swirling about a potential "SUPER" semi-successor. Sections of NVIDIA's previous-gen "Ada Lovelace" GeForce RTX 40-series family received mid-generation refresh treatment around early 2024. It is not clear whether it will take a year+ for the speculated arrival of upgraded "Blackwell" desktop gaming solutions, but members of the Chiphell forum have been openly discussing alleged "in-progress" GeForce RTX 5080 SUPER 24 GB and RTX 5070 SUPER 18 GB card designs. Past weekend theorizations were highlighted by ITHome and VideoCardz—in particular, one Chiphell participant posited the two follow-ups will not be deployed with noticeably "faster" performance.

Larger pools of onboard GDDR7 VRAM could pave the way for improvements in AI productivity, although greater capacities could lead to beneficial conditions in gaming scenarios—e.g. extra provisions for large textures and complex assets. The speculated GeForce RTX 5080 SUPER card could borrow aspects from Team Green's GeForce RTX 5090 Mobile 24 GB model; namely the latter's usage of 3 GB GDDR7 memory modules. Press interpretations—of fresh Chiphell leaks—point to company engineers enabling existing PCB designs with 8×3 GB (24 GB) and 6×3 GB (18 GB) parts; thus preventing a major overhaul of board layouts. Global PC gaming hardware communities have often expressed a dislike of NVIDIA's repeated deployment of 8 GB and 12 GB capacity products. A theoretical GeForce RTX 5070 SUPER 18 GB option could receive a warmer welcome. Very early speculation proposes an introduction—of SUPER "Blackwell" models—just before or during CES 2026.

Not long after Intel's launch of the Arc Xe2 "Battlemage" B580 12 GB graphics card design, insiders started generating noise about potential spin-offs bound for release in 2025. In theory, the speculated "B580 24 GB" variant could arrive as a workstation-oriented discrete graphics solution—possibly lined up as a next-gen entry within Team Blue's Arc Pro family. Three mysterious BMG (aka "Battlemage") PCI identifiers turned up at the end of January; sending online PC hardware debates into overdrive; one faction believed that Team Blue was readying fabled productivity-focused B-series cards—complete with enlarged pools of GDDR6 VRAM. Apparently, Sparkle's Chinese branch has provided comment on newer rumors—from March, according to VideoCardz. The Taiwanese manufacturer is a key Intel board partner in the field of Arc GPU-based graphics card products—across gaming and professional desktop lines. Unfortunately, the company's head office (in Taiwan) has dismissed "official" claims about a May/June launch of an unnamed 24 GB model. Sparkle's Chinese social media account engaged with members of the PC hardware community, and outlined an "original plan" to release something new within the second quarter of 2025—apparently the incoming card is "still being arranged."

MSI made at least two typos and corrections spaced apart from each other that hint at the possibility of a 24 GB variant of the NVIDIA GeForce RTX 5080. The first instance was on the side of the retail box of an RTX 5080 Vanguard OC Launch Edition, which had "24 GB GDDR7" printed on top of the RTX 5080 label. The second instance was in the VGA Support list in the product page of the MAG X870 Tomahawk motherboard, where the memory size is displayed as 24,576 MB (24 GB). There are two possible interpretations of this.

One possibility is that NVIDIA originally planned the RTX 5080 to feature 24 GB of memory, using 3 GB (24 Gbit) GDDR7 memory chips across the 256-bit wide memory bus of the "GB203" silicon, and initially communicated this to its board partners, but revised the specs in the months leading up to the launch, with the card ending up with 16 GB (8x 16 Gbit). The other possibility is that there is actually a 24 GB variant in the works, which NVIDIA could end up calling the "RTX 5080 24 GB." The RTX 5080 in the market already maxes out the "GB203" silicon it's based on, so the variant could just offer a 50% increase in memory size at the same or similar memory bandwidth. The additional memory could come in handy with 4K Ultra HD + ray tracing + DLSS 4 MFG scenarios where a gamer is looking to turn their roughly 60 FPS framerates to match the 120 Hz refresh rates of their displays.

MSI's latest high-end gaming laptops, including the Titan 18 HX AI, Raider 18 HX AI, and Vector 16 HX AI, feature Intel Core Ultra 200 HX series CPUs and NVIDIA RTX 50 series GPUs, while Raider A18 HX and Vector A18 HX run on AMD Ryzen 9000 series. With NVIDIA's last major GPU upgrade in over two years, these laptops deliver top-tier performance for ultra-high-resolution gaming. Beyond gaming, MSI's Titan, Raider, Vector, and Stealth series excel in AI applications, particularly Small Language Models (SLM), making them ideal for both gaming and AI-driven tasks.

Next-Gen GPUs: A Breakthrough for AI Applications
NVIDIA's latest RTX 50 series GPUs, built on the cutting-edge Blackwell architecture, introduce 5th-generation Tensor Cores, 4th-generation RT Cores, and Neural Rendering technology for the first time. With expanded memory capacity and GDDR7, these GPUs optimize AI-enhanced neural computations, reducing memory usage while boosting graphics rendering and AI processing efficiency. This results in unmatched performance for both gaming and creative workloads, enabling smoother, more efficient execution of complex tasks.

G.SKILL International Enterprise Co., Ltd., the world's leading brand of performance overclock memory and PC components, is excited to announce the release of three new DDR5 memory specifications with AMD EXPO OC profiles for AMD platforms, including an extreme speed with low-latency at DDR5-8000 CL36-48-48 48 GB (24 GB x2), large-capacity & low-latency DDR5-6000 CL28-36-36 192 GB (48 GB x4), and a new DDR5-6000 CL26-39-39 with 48 GB (24 GB x2) kit capacity. Designed for PC enthusiasts, gamers, content creators, and AI applications, these cutting-edge DDR5 memory kits push the boundaries of speed, latency, and capacity on AMD AM5 platforms.

Pushing the Limits with Extreme DDR5-8000 CL36 24 GB x2
For users seeking top-tier performance, the new DDR5-8000 CL36-48-48 24 GB x2 memory kit with AMD EXPO OC profile is engineered for ultra-high memory speed at low CL36 latency timings. This extreme-speed and low-latency combination is ideal for exceptional system responsiveness and multitasking performance. See below for the Memtest validation screenshot showcasing its stability on the ASUS ROG Crosshair X870E Hero motherboard and AMD Ryzen 9 9900X desktop processor.

This month, we at AMD celebrate two significant milestones in the Radeon story. First, the 25th anniversary of Radeon, a journey that began in 2000 with the ATI Radeon DDR card. Back then, 32 MB of VRAM, a 143 MHz clocks, and 30M transistors were cutting-edge tools that sparked your early adventures. Today, those specs are a nostalgic memory, dwarfed by the leaps we've made together culminating in the 24 GB of memory, multi-GHz clocks, and nearly 60B transistors of RDNA 3 cards driving the immersive worlds you now explore. But we're not stopping there. We're proud to continue that innovation journey with the RDNA 4-based Radeon RX 9070 XT and Radeon RX 9070, available starting today. This is more than a new chapter for us, it's a promise to you, the gamers who fuel our passion. We know what matters when you choose your next GPU: raw performance to conquer your favorite titles, tech that's ready for tomorrow's blockbusters, and value that respects your investment. That's precisely what RDNA 4 delivers.

Our goal with RDNA 4 wasn't to chase an elite crown few can reach. Instead, we focused on you, the heart of gaming, crafting cards that bring exceptional power to the setups most of you run. Compared to our last gen, RDNA 4 boosts raster performance for crisper, smoother visuals. Ray tracing throughput doubles, letting you soak in lifelike lighting and reflections without compromise. And with an 8x uplift in machine learning performance, we're unlocking new possibilities - like FSR 4, our latest leap in ML-based upscaling.

Apple's unannounced M4 MacBook Air family is likely reaching market availability status at some point next month. Last December, slimline notebook enthusiasts started hearing about an updated lineup; macOS's Sequoia 15.2 update reportedly referenced upcoming MacBook Air M4 13-inch and 15-inch models. An early sample unit—named "Mac16,12"—has participated in a Geekbench 6.4.0 (macOS AArch64) gauntlet; results appeared online yesterday. The alleged "MacBook Air 13" candidate posted an overall Metal score of 54,806, and an overall OpenCL tally of 36,305. The two separate Geekbench Browser entries confirm that the sampled device makes use of a 10-core M4 processor, with Cluster 1 containing four performance cores. Cluster 2 consists of six power efficiency-oriented cores. Base frequency is listed at 4.41 GHz; reportedly the highest recorded for an M4 SoC. Said chip accessed 24 GB of unified memory, during its macOS 15.2 (Build 24C2101)-based test session.

Notebookcheck and Wccftech compared the aforementioned data points with slightly older M4-equipped hardware, including a premium model. Both outlets observed a "measly" five percent performance difference. Elaborating on their findings, Notebookcheck stated: "as always, we would recommend taking early benchmark results with a healthy amount of skepticism for the time being. With that being said, the MacBook Air 13 benchmarked falls about 5% short of the median Geekbench OpenCL and Geekbench Metal results we achieved so far when benchmarking the M4 versions of Apple's Mac Mini and MacBook Pro 14." The rumored next-gen MacBook Air is expected to operate with a fan-less cooling system—press outlets reckon that the MacBook Pro's air-cooled operation puts it at a slight advantage (in benchmarks).

Last month, ASUS revealed its refreshed ROG XG Mobile design at CES 2025. The latest iteration of their premium external GPU dock is prepped for NVIDIA's "Blackwell" GeForce RTX 50 Mobile GPU-series. According to an ITHome report, the new model will be released next week; the manufacturer's Chinese office has seemingly produced marketing material that teases a launch on February 25. The redesigned ROG XG platform leverages an improved vapor chamber system; offering "150% more cooling surface area," and features "pioneering" Thunderbolt 5 connectivity (max. 80 Gbps bidirectional bandwidth). Press material from January indicated that a top configuration would house Team Green's GeForce RTX 5090 Mobile 24 GB GPU.

An updated official product page also lists support for NVIDIA's "GeForce RTX 5070 Ti Laptop" 12 GB GPU. ASUS will bundle in a 330 W AC adapter, according to its spec sheet. The off-black translucent enclosure weighs in at 0.952 kg, and dimensions are listed as: "20.8 x 15.5 x 2.96 cm." ITHome expects ASUS to reveal regional pricing (for China) on February 25; Western markets will be charged $2199.99 (US MSRP) for the flagship configuration, if price hikes do not go into effect at launch. The less potent variant—powered by a GB205 GPU—is priced at $1199.99.

At the 2025 International CES, we went hands on with some of the first Schenker XMG enthusiast notebooks that feature a next-generation NVIDIA GeForce RTX 5090 Laptop GPU. These include the Schenker Key 18 PRO, and the XMG Neo 16. The Key 18 Pro is a massive portable workstation featuring an 18-inch 16:10 display with either 2560 x 1600 or 3840 x 2400 pixels resolution, with either 500 nits or 400 nits brightness, respectively. The notebook is powered by an Intel Core Ultra 9 275HX processor (8P+16E, 36 MB cache), with four DDR5 SODIMM slots that you can add up to 192 GB of memory to. The star attraction of course is its NVIDIA GeForce RTX 5090 Laptop GPU, which is configured with 24 GB of video memory, and 175 W of power. A large 98 Wh battery powers the beast.

Meanwhile, the XMG Neo 16, as its name suggests, has a 16-inch display. This is 16:10, with 2560 x 1600 resolution, comes with 300 Hz refresh rate, and 1000 nits brightness. You get the same combination of a Core Ultra 9 275HX processor and GeForce RTX 5090 Laptop GPU, with the GPU getting 175 W of power. There are two DDR5 CSODIMM slots (SODIMMs with CKD). The company also showed off two of its key innovations that power the two notebooks, its mainboard with a proprietary bridge connector between the motherboard and discrete GPU board; and its two new cooling solutions.

G.SKILL International Enterprise Co., Ltd, the world's leading brand of performance overclock memory and PC components, is thrilled to release new low CAS latency memory kits featuring AMD EXPO overclock profile for the new AMD Ryzen 9000 series processors and performance X870 chipset motherboards. These new specifications include DDR5-6000 CL26 2x16GB/2x32GB kits and 2x 24 GB/2x 48 GB memory kits under the Trident Z5 Royal Neo, Trident Z5 Neo RGB, and Ripjaws M5 RGB Neo series.

Aiming to provide high-performance overclock DDR5 memory for PC enthusiasts, G.SKILL is releasing a new low CAS Latency memory kit at DDR5-6000 CL26-36-36-96 with kit capacity configuration of 32 GB (2x16GB), as well as the world's first 64 GB (2x32GB) kit capacity for this low latency specification. Featuring the AMD EXPO memory overclocking profile, these new specifications are built for selected X870 series motherboards and AMD Ryzen 9000 series processors. The screenshot below demonstrates DDR5-6000 CL26 2x32GB kit's stability under the Memtest memory stress test on the ASUS ROG Crosshair X870E Hero motherboard and AMD Ryzen 9 9900X desktop processor.

Intel could be working on a new Arc graphics card according to Quantum Bits quoted by VideoCardz. It's based on the Battlemage architecture and has 24 GB of memory, twice as much as current models. This new card seems to be oriented more towards professionals, not gamers. Intel's Battlemage lineup currently has the Arc B580 model with 12 GB GDDR6 memory and a 192-bit bus. There's also the upcoming B570 with 10 GB and a 160-bit bus. The new 24 GB model will use the same BGM-G21 GPU as the B580, while the increased VRAM version could use higher capacity memory modules or a dual-sided module setup. No further technical details are available at this moment.

Intel looks to be aiming this 24 GB version at professional tasks such as artificial intelligence jobs like Large Language Models (LLMs) and generative AI. The card would be useful in data centers, edge computing, schools, and research, and this makes sense for Intel as they don't have a high-memory GPU for professional productivity markets yet. The company wants to launch this Arc Battlemage with bigger memory in 2025, we guess it might be announced in late spring or ahead of next year's Computex if there's no rush. Intel in the meantime will keep making their current gaming cards too as the latest Arc series was very well received, a big win for Intel after all the struggles. This rumor hints that Intel's expanding its GPU plan rather than letting it fade away, that was a gray scenario before the launch of Battlemage. Now it seems they want to compete in the professional and AI acceleration markets as well.

Kingston Technology Company, Inc., a world leader in memory products, announced the upcoming release of Kingston FURY Renegade DDR5 CUDIMMs, compatible with Intel's new 800-series chipset (formerly codenamed Arrow Lake). Intel's 800-series chipset is the first platform to utilize Clock Drivers on CUDIMMs (Clocked Unbuffered Dual Inline Memory Modules). At 6400 MT/s DDR5, JEDEC mandates the inclusion of a Client Clock Driver (CKD) on UDIMMs and SODIMMs. This component buffers and redrives the clock signal from the processor, enhancing signal integrity to the module. To distinguish these advanced modules from standard DDR5 UDIMMs and SODIMMs, JEDEC has designated them as CUDIMMs and CSODIMMs, respectively.

Kingston FURY Renegade RGB and non-RGB CUDIMM modules start at an overclocked speed of 8400 MT/s and are available as 24 GB single modules and 48 GB dual channel kits. Since CUDIMMs and UDIMMs share the same 288-pin connector, Kingston FURY UDIMMs with XMP and EXPO profiles are also compatible with Intel 800-series motherboards. However, it's recommended to verify compatibility through the motherboard manufacturer's QVL (Qualified Vendor List) or by checking the Kingston Configurator for supported speeds and capacities.

The world's leading brand for memory modules and flash memory and long-term Intel partner, ADATA Technology and its gaming brand XPG (Xtreme Performance Gear) today announced the launch of new DDR5 CUDIMM memory, including XPG LANCER RGB DDR5 CUDIMM gaming memory and ADATA DDR5 CUDIMM memory, supporting the latest Intel Core Ultra Desktop Processor (Series 2) and providing a variety of options that satisfy the needs of extreme gamers and general users.

DDR5 CUDIMM features a base clock speed starting at 6,400MT/s and is equipped with a key CKD (Clock Driver) component which ensures stable operation at high frequencies. It is compatible with existing Intel Core Desktop Processors and memory speed can easily top 9,000MT/s when overclocked on a Z890 motherboard. This DDR5 CUDIMM is expected to be a powerful next-generation DDR5 memory, greatly improving the processing efficiency and stability of desktop platforms.

Samsung Electronics, the world leader in advanced memory technology, today announced it has begun mass production for the industry's thinnest 12 nanometer (nm)-class, 12-gigabyte (GB) and 16 GB LPDDR5X DRAM packages, solidifying its leadership in the low-power DRAM market. Leveraging its extensive expertise in chip packaging, Samsung is able to deliver ultra-slim LPDDR5X DRAM packages that can create additional space within mobile devices, facilitating better airflow. This supports easier thermal control, a factor that is becoming increasingly critical especially for high-performance applications with advanced features such as on-device AI.

"Samsung's LPDDR5X DRAM sets a new standard for high-performance on-device AI solutions, offering not only superior LPDDR performance but also advanced thermal management in an ultra-compact package," said YongCheol Bae, Executive Vice President of Memory Product Planning at Samsung Electronics. "We are committed to continuous innovation through close collaboration with our customers, delivering solutions that meet the future needs of the low-power DRAM market."