News Posts matching #GDDR7

Return to Keyword Browsing

NVIDIA GeForce RTX 60-Series Reportedly Slips to 2028, Per New Leak

Kopite7Kimi, a leaker with a strong track record on NVIDIA hardware, says the company's next-generation GeForce RTX 60-series based on the Rubin architecture is a 2028 product. "Unfortunately, GR20x is a product from 2028. That means they have postponed again," the leaker posted on X. Their earlier estimate was the second half of 2027, so this is another "delay," if you can even call it that. NVIDIA hasn't said anything official about RTX 60-series timing, so treat it as a rumor for now.

Interestingly, this new leak seems to align with what prominent leaker Kepler_L2 claimed a few days ago: that Rubin gaming GPUs would only arrive in 2028. It also goes against leaker Moore's Law Is Dead, who said about a week ago that an NVIDIA source told them gaming Rubin was greenlit for the first half of 2027. Two leakers against one doesn't settle anything, and we don't know who is right yet, but the 2028 timing does seem more likely given the current industry conditions. Of course, these plans can change before 2028, as the memory supply situation is currently very volatile, and hardware roadmaps are changing almost on a weekly basis.

NVIDIA Unveils RTX PRO 5500 "Blackwell" Workstation GPU with 84 GB GDDR7 Memory

NVIDIA today quietly added another card to its pro-viz product lineup with the RTX PRO 5500 "Blackwell" workstation GPU edition. Featuring 84 GB of GDDR7 memory, it is equipped with a GB202 die that includes 21,760 CUDA cores. This is the same CUDA core count as the consumer GeForce RTX 5090 SKU, but it is now certified for professional workloads and has a much higher memory capacity. The 84 GB of GDDR7 is connected to the GB202 with a 416-bit memory bus that delivers about 1,398 GB/s of memory bandwidth. This would put each GDDR7 memory chip at about 26 Gbps per pin, which is a standard GDDR7 memory speed, but not the fastest available on the market. Additionally, to achieve the massive 84 GB capacity, there need to be 28 memory modules. NVIDIA placed 14 GDDR7 modules on the front side with the GPU die and 14 GDDR7 modules on the back of the PCB, effectively sandwiching the PCB.

Compared to the rest of the RTX PRO lineup, the new RTX PRO 5500 "Blackwell" sits just a tick below the flagship RTX PRO 6000 SKU, which has a slightly higher CUDA core count of 24,064 and a 96 GB memory capacity. However, the RTX PRO 5500 is also much more powerful than the RTX PRO 5000 in the 5000 tier. The RTX PRO 5000 "Blackwell" has a much lower CUDA core count of 14,080 cores, with up to 72 GB of memory. Technically, the new SKU is much closer to the RTX PRO 6000 than the RTX PRO 5000 SKU, just with a slightly lower core count and memory capacity. The official specification sheet follows, courtesy of PNY.

Modified GeForce RTX 5090 with 96 GB Memory Shows Up on Alibaba for Nearly $4,000

A Chinese manufacturer is now selling a modified GeForce RTX 5090 with 96 GB of memory, three times the 32 GB on the retail card. Shenzhen Suqiao Intelligent Technology, an OEM/ODM with over a decade of experience building graphics cards, motherboards, and servers, listed the card on Alibaba for $3,888. That's roughly 35% less than a standard RTX 5090 currently costs in the US, and a fraction of what NVIDIA charges for its RTX PRO 6000 Blackwell. The latter uses the same GB202 die and now starts at a whopping $16,000.

Suqiao likely built this with a custom PCB running clamshell memory, packing GDDR7 modules on both sides of the board to double capacity, the same approach NVIDIA itself uses on the Pro 6000. The GPU die may come from harvested RTX 5090 units, reballed onto the new board and running on leaked or modified firmware, a method Chinese workshops already used to push the RTX 4090 to 48 GB VRAM. The listing does raise some doubts, though, since it mentions GDDR6X memory at 14 Gbps, which doesn't line up with a genuine 96 GB Blackwell build.

NVIDIA RTX 5090 Shoots Past €5,000 in Germany, Prices Jump 73% Since January

GeForce RTX 5090 prices in Germany have now pushed past €5,000, with the cheapest listed model on Geizhals coming in at €5,242.94 for the INNO3D iCHILL Frostbite Pro. Hardwareluxx, which first flagged the price increase, reports that there isn't a single RTX 5090 currently listed below €5,200 in the German market, and several mainstream models are edging toward €5,500. The same card was going for around €3,029 back in January, so that's roughly a 73% jump in eight months. NVIDIA's Founders Edition RTX 5090, when it's actually in stock, is still priced at €2,099, meaning custom cards now cost well over double that.

Germany isn't alone in this crisis. RTX 5090 pricing in the US recently crossed $5,000 too, and NVIDIA hasn't addressed either situation publicly. Instead, the company appears to be leaning on event-based promotions, like the one it ran at PAX West, to hand out occasional MSRP units rather than dealing with the overall pricing problem. The rising cost of GDDR7 memory tied to AI demand appears to be the main driver, and board partners have apparently been passing those costs straight to consumers for months.

Gamers Buy More GPUs Than Ever in Q2 2026, Even as Prices Keep Climbing

Desktop graphics card shipments hit 12.5 million units in Q2 2026, the highest quarterly total since Q1 2022, according to new data from Jon Peddie Research. That's a 5.9% jump from the previous quarter and a 7.8% increase year over year, despite GPU prices climbing for months. For the first half of 2026, desktop AIB shipments reached 24.3 million units, up from 20.8 million over the same stretch last year. This spike is interesting partly because of the timing, since the industry is facing a severe memory crisis. VRAM costs have been rising steadily, and GPU makers have already pushed through several rounds of price increases on entry-level and high-end cards alike.

Jon Peddie, president of JPR, thinks that the price hikes are actually feeding the shipment growth rather than slowing it. Common sense dictates that rising prices will adversely affect sales, as gamers will tend to stick with their existing GPUs rather than spending big on a new upgrade. However, Jon's theory is that gamers are buying now because they expect prices to climb further, especially as GDDR7 costs keep rising. Apparently, the fear of missing a better price is doing more to move units right now than the higher prices are doing to scare buyers away.

Manli Intros UF (Unlimited Firepower) GeForce RTX 50 Graphics Cards Series

Manli is marking its 30th anniversary with the launch of the UF (Unlimited Firepower) series, a new graphics card lineup that joins its existing Nebula, Stellar, Polar Fox, and Gallardo families. Currently, it seems that two models are available at launch, both based on NVIDIA Blackwell architecture: the Manli UF GeForce RTX 5060 OC and the UF RTX 5060 Ti OC. Both are 2-slot cards measuring 324 x 143 x 42 mm with triple 92 mm fans, an aluminium baseplate, large radiators, and three 6 mm composite copper heatpipes. Idle fan stop is supported. Both graphics cards have 8 GB GDDR7 memory with a 128-bit interface, 28 Gbps speed, and 448 GB/s bandwidth. For connectivity, three DisplayPort outputs and one HDMI are available. On the GPU side, the RTX 5060 OC has 3,840 CUDA cores at 2280/2550 MHz base/boost and draws 145 W. The RTX 5060 Ti OC steps up to 4,608 CUDA cores at 2407/2632 MHz base/boost and a 180 W TDP.

A notable feature on both cards is G-Sense, a built-in tilt sensor that monitors GPU alignment in real time and sends alerts through a new Manli App if abnormal sag is detected. The app also handles ARGB customization and hardware monitoring. No pricing or store availability has been announced yet.

ASUS and Galax Raise GeForce RTX 50-Series Prices by Up to $74

ASUS and Galax have become the latest NVIDIA board partners to raise prices on RTX 50-series cards, with increases landing September 1. According to a report from Channel Gate, ASUS is bumping RTX 5070 prices by 150 to 300 Yuan, or roughly $22 to $44, while Galax is applying a 200 Yuan (about $30) hike to the same card. Galax's RTX 5070 Ti is going up 300 Yuan (around $44), and its RTX 5080 sees the steepest jump at 500 Yuan (about $74). Budget cards like the RTX 5060 and RTX 5050, along with the flagship RTX 5090, are apparently untouched this time. The increases here are smaller in dollar terms than some earlier hikes, but they add up, and mid-range buyers eyeing the RTX 5070 family are in the crosshairs this time.

This is likely the third or fourth 2026 price hike for NVIDIA's board partners, and it results from the GDDR7 cost pressure we have tracked for months. NVIDIA reportedly raised the price of its GPU-memory kits for partners back in July, and that increase still seems to be trickling down one vendor at a time. NVIDIA had already raised prices on the RTX 5090 specifically in May for the same reason. With ASUS and Galax moving this week, other partners like MSI, Gigabyte, and Colorful will probably follow with adjustments of their own soon, since that's been the pattern all year. Right now, there seems to be no plausible end in sight either.

Micron Explores Near-GPU NAND Flash to Run Bigger LLMs

Micron is reportedly exploring the idea of developing high-endurance NAND Flash modules that would be positioned closer to the GPU, rather than being located far away in the storage pool behind multiple protocols. The company is said to be investigating ways to bring NAND Flash closer to handle workloads that don't require the latency and bandwidth of traditional HBM or regular DRAM modules. This architecture, currently referred to as "near-GPU NAND," would serve as a middle ground between density and durability. This concept would allow GPUs to access a pool of NAND Flash that has a lower density than conventional TLC or QLC NAND, but instead focuses on improving I/O speeds, bandwidth, and read times.

For instance, this would enable a GPU to access a potential storage pool with hundreds of gigabytes of storage directly on the GPU package or PCB, similar to what DRAM like HBM or GDDR7/LPDDR6 already does. This tier would sit between GPU memory and regular system storage, acting as a very fast buffer, which would be ideal for the inference of massive LLMs. At that point, LLMs wouldn't be memory-bound and could run on systems with fewer GPUs, but with more storage and memory tiers to compensate for the required inference size. Additionally, this NAND would be significantly cheaper than HBM or regular DRAM and would be sized according to system specifications. Images below are HBF slides from SK hynix and Sandisk.

GPU Prices Jumped 15% in One Month, RTX 5090 Now 136% Above MSRP

GPU prices just climbed 15% in a single month, according to fresh pricing data tracked across 10 countries by TechSpot. When averaged across all graphics card models, the market now sits 28% above launch MSRP, excluding the RTX 5090. TechSpot excluded the RTX 5090 because it is an extreme outlier, and they say it's not really a gaming GPU. NVIDIA still lists it at $1,999, but the cheapest available model in the US now costs nearly $5,000, or 145% above MSRP domestically and 136% globally.

On average, GeForce cards overall rose 19% month over month, while Radeon GPUs rose 11%. That aligns with earlier reporting that RTX 50-series prices climbed as much as 41% in a single month, so this appears to be a continuation of that trend. The RTX 5060 Ti 16GB is now the second-most inflated card on the list, priced 70% above its $429 MSRP in the US and 53% above MSRP globally. Meanwhile, its 8GB sibling sits at just 14% above MSRP worldwide, which makes this split very interesting.

NVIDIA's "Rubin CPX" GPU Reborn with HBM4 Memory, No More GDDR7

NVIDIA has reportedly revived its "Rubin CPX" AI accelerator project, which had previously been put on hold. Today, well-known supply chain analyst Ming Chi Kuo reported that NVIDIA is reintroducing the "Rubin CPX," now featuring HBM4 memory instead of the previously planned GDDR7. Late last year, NVIDIA announced its plans to develop a specialized accelerator derived from the "Rubin" GPU family, designed for large-scale agentic AI workloads. After the announcement, the project was reportedly paused, but NVIDIA has now redesigned the memory architecture. Previously, the "Rubin CPX" was slated to have 128 GB of GDDR7 memory, but it will now include 168 GB of HBM4 memory. This GPU SKU is housed in a separate rack with configurations ranging from 64 to 256 standalone CPX GPUs per rack.

This GPU is dedicated to prefill workloads, powering racks that manage input context for LLMs and KV cache processing. Essentially, NVIDIA is separating prefill from decode tasks, with CPX GPUs handling prefill and regular "Rubin" GPUs managing decode. A rack tray with eight CPX GPUs can handle 1.34 TB of long-context prefill and the associated KV cache, all utilizing HBM4 memory for faster processing and increased bandwidth. Since the previous design did not require HBM4 integration, NVIDIA has redesigned the package, likely using TSMC's CoWoS-S or CoWoS-L for packaging.

NVIDIA GeForce RTX 5060 with GB205 Appears in Third-Party AIB Design

NVIDIA's GeForce RTX 5060 mid-range graphics card is officially based on the GB206 GPU die SKU, equipped with 3,840 CUDA cores, 120 TMUs, 48 ROPs, and a total of 8 GB of GDDR7 memory running on a 128-bit bus. This is the standard configuration, which is supposed to be the same across every RTX 5060 GPU you buy from any of NVIDIA's add-in board partners. However, a review of the ASUS DUAL GeForce RTX 5060 OC D7 8 GB by Intek & Company, Quasar Zone revealed that the GPU die inside this graphics card is actually a GB205-200-KB-A1 GPU die SKU. This die is usually found in NVIDIA's GeForce RTX 5070, RTX 5070 Ti Mobile, and RTX PRO 3000 "Blackwell" mobile graphics cards.

When NVIDIA does these GPU SKU crossovers, it usually comes down to binning. Sometimes, GPUs of a lower bin do not meet all the parametric yields, meaning not all CUDA cores are functional. In such cases, the company can repurpose these GPUs as a lower-tier design, as is the case with the RTX 5060. Instead of this SKU going into an RTX 5070 and lacking CUDA cores, ROPs, or TMUs, it is cut down to RTX 5060 specs and used as an RTX 5060 base. No performance difference should be present.

LACT Brings More NVIDIA OC Controls and GPU Sensors to Linux

Linux GPU overclocking and monitoring tool, LACT, has officially launched v0.10.0, adding a host of new overclocking and sensor options for NVIDIA GPUs. The update notes mention PowerMizer mode, which allows users to force the NVIDIA GPUs into the highest p-state. The update also adds "Voltage boost," a new slider that allows the GPU to draw more voltage—as opposed to a more traditional voltage offset slider. The developers note that this slider merely adds more headroom for certain overclocks.

The update also adds new sensor read-outs for both NVIDIA and AMD GPUs. NVIDIA users on Blackwell GPUs now have access to hotspot sensors and per-memory-chip temperature sensors for both GDDR6x and GDDR7. On the AMD side of things, there is now support for graphical GTT memory display—GPU-accessible system memory—which is noted to be particularly helpful for iGPUs in high-memory-load applications and games, but may also be helpful when using older, low-VRAM GPUs, since those may also require spilling over into system memory more often. Check out the full update notes for more.

NVIDIA RTX PRO 6000 "Blackwell" 96 GB GPU Now Costs $16,000

If you thought consumer graphics card prices were bad, the situation isn't much better on the workstation front. According to an update on NVIDIA's marketplace, the company's flagship workstation card—the RTX PRO 6000 "Blackwell"—is now retailing for $16,000. This makes it the most expensive GPU that NVIDIA sells outside of its server offerings like the B200/B300, which come in the SXM form factor. Even for a graphics card equipped with 24,064 CUDA cores and 96 GB of GDDR7 memory, this price is astonishing and show just how much memory shortages are impacting GPU pricing. For a SKU that features 32 GDDR7 memory modules, each with a 3 GB capacity, any increase in supply chain costs is instantly multiplied by 32 for this very expensive component.

On the RTX PRO 6000 "Blackwell" GPU, there are 16 GDDR7 modules on the front side with the GPU die and 16 GDDR7 modules on the back of the PCB, effectively sandwiching the PCB. This results in 32 modules spread across the GPU. Back in late July, each 3 GB GDDR7 module cost about $60 to $70, so the total cost of the GDDR7 alone ranged from $1,920 to $2,240. This is the price of what is essentially a raw material, crucial for manufacturing this SKU. Considering that there might be additional GDDR7 price increases now, NVIDIA has priced its flagship workstation SKU at $16,000, accounting for many other component costs, such as MLCCs, which are also in tight supply.

NVIDIA GeForce RTX 50 Series Faces 30% Price Increase in South Korea

NVIDIA's GeForce RTX 50 series is rumored to see a price increase of about 20-30%, depending on the model, due to rapidly rising costs of GDDR7 memory from NVIDIA's VRAM suppliers. According to ZDNet Korea, South Korean importers and distributors have already informed the supply chain about this price hike, which could reach up to 30%. NVIDIA provides its add-in board partners with GDDR7 memory as a kit that includes both the GPU die and GDDR7, so any price increase from memory manufacturers affects AIBs and, ultimately, consumers.

Currently, each 2 GB GDDR7 memory module costs in the low 20s in USD. This spot pricing for GDDR7 means NVIDIA needs 16 of these modules for its flagship GeForce RTX 5090 GPU. This results in at least $320 being spent on GDDR7 memory for the flagship model, before adding the cost of the GPU die, research and development, and the margins for AIB partners. The situation remains challenging even in South Korea, the world's hub of DRAM production. Despite being home to SK hynix and Samsung, no one is exempt from these price increases, which are expected to continue.

NVIDIA Reportedly Raises GDDR6 and GDDR7 Memory Kit Prices for RTX GPUs

NVIDIA has reportedly notified its add-in card partners of another GPU kit price increase, this time covering both GDDR7 and GDDR6 memory. This means the raise isn't limited to current Blackwell cards and could affect older GeForce products still using GDDR6 as well. The report comes from BenchLife via VideoCardz and follows a similar price adjustment for the RTX 5090 and RTX 5090D V2 back in May. NVIDIA supplies board partners with GPU and VRAM bundled together as a kit, so when memory costs go up, AIBs have little choice but to pass that along to retail pricing. BenchLife notes that partners are also seeing higher costs for coolers, PCBs, and packaging on top of the memory increases, though those secondary cost pressures are described as smaller than the memory-related ones.

The RTX 50 SUPER series is also affected by this. We've previously reported that those cards are on hold partly due to the cost of 3 GB GDDR7 modules. Inside sources say that each of those GDDR7 modules costs about $60-$70, roughly three times the cost of a 2 GB module at around $20. This adds a significant price premium on SUPER cards since the RTX 5070 SUPER was expected to be upgraded to offer 18 GB, while the RTX 5070 Ti SUPER and RTX 5080 SUPER would each provide 24 GB of GDDR7 memory. GPU prices have already increased 20-30% above where they were not long ago, and this latest round of kit price increases suggests there's more pressure to come. Previous-gen cards that use GDDR6 have been less affected up to now, but that appears to be changing.

Per-Module GDDR7 Temperature Reading Unlocked on NVIDIA GeForce RTX 50 "Blackwell"

More individual readings are being unlocked on NVIDIA's GeForce RTX 50 series "Blackwell" graphics cards, as the modding community has started exploring GDDR7 temperature monitoring on a per-module basis. Interestingly, the modding community is diverse this time, including contributions from Brazilian GPU repair specialist Paulo Gomes, MSI Afterburner developer "Unwinder," Overclock.net member "asder00," HWiNFO creator Martin "Mumak" Malík, and Linux code developer "olealgoritme." By joining forces, the team managed to create a plugin for MSI Afterburner that provides access to individual, per-module GDDR7 temperature readings.

This new Hotspot.dll plugin, which previously only provided access to the hidden "Blackwell" GPU die, is now updated to handle GDDR7 temperature readings, unlocking the GDDR7 thermal sensors hidden inside memory ICs. For example, on the GeForce RTX 5090 GPU, there are 16 GDDR7 memory modules, each with a 2 GB capacity. Since there are 16 chips, the tool can read 16 temperature sensors and provide 16 individual readings. However, some GDDR7-equipped "Blackwell" GPUs use a clamshell memory configuration, meaning the GDDR memory is on both sides of the PCB. For example, in the case of the RTX PRO 6000 "Blackwell", this would mean only half the measurement points, as the GDDR7 memory is present in 16 locations on both sides of the PCB, for a total of 32 memory modules.

NVIDIA Board Partners Receive RTX 50 SUPER, But GDDR7 Pricing Holds the Release Back

NVIDIA's long-rumored GeForce RTX 50 SUPER graphics cards have been shipped to the company's board partners, but we can't get our hands on them just yet. According to VideoCardz, NVIDIA's board partners have already received the GeForce RTX 50 SUPER silicon, but the release is on hold by Team Green headquarters. This means that while the GPUs are physically with the board partners, they can't proceed with the launch due to a shortage of GDDR7 memory chips. It was previously rumored that the "SUPER" series was planned to feature denser GDDR7 memory modules, offering 3 GB of capacity per chip, which would increase the memory configuration of the standard GeForce RTX 5070, RTX 5070 Ti, and RTX 5080. Initially, the RTX 5070 SUPER was expected to be upgraded to offer 18 GB, while the RTX 5070 Ti SUPER and RTX 5080 SUPER would each provide 24 GB of GDDR7 memory.

Meanwhile, all other specifications will remain the same. However, since the 3 GB GDDR7 memory modules are being used in other products like NVIDIA's AI GPU portfolio, including the RTX PRO 6000 "Blackwell" and "Rubin CPX," the company has likely decided to prioritize this high-margin business. The availability of 3 GB GDDR7 modules is much lower than the current industry demand. As a result, gamers are left with the regular GeForce RTX 50 series for now, which uses the more readily available 2 GB GDDR7 memory modules.

NVIDIA Readies GeForce RTX 5090 SE Graphics Card

NVIDIA is readying the new GeForce RTX 5090 SE graphics card, according to a report by GameGPU. This SKU could fill the gap between the current RTX 5080 and the flagship RTX 5090. Unlike the RTX 5090D and RTX 5090D V2, the RTX 5090 SE isn't a region-specific SKU aimed at complying with U.S. AI accelerator export controls, but is rather a mainline gaming GPU product. It is based on the same "GB202" silicon as the RTX 5090, but is cut down from it, featuring fewer streaming multiprocessors (SM), and a narrower 384-bit wide GDDR7 memory interface. The memory size is still 32 GB, achieved using a mixed density of 24 Gb and 16 Gb memory chips.

NVIDIA is carving the RTX 5090 SE out of the "GB202" by enabling 110 out of the 192 SM physically present on the silicon, resulting in 14,080 CUDA cores, 110 RT cores, 440 Tensor cores, 440 TMUs, and an unknown ROP count, probably 144. Meanwhile, the TGP of the RTX 5090 SE is expected to be around 500 W, down from 575 W of the RTX 5090. NVIDIA is looking to target a launch MSRP of $1,500, but you can be sure that the street price will be much higher.

AI Server Demand Continues to Support Memory Prices in 3Q26, but Gains Moderate as Consumer Demand Weakens and High Base Effects Take Hold

TrendForce's latest memory pricing survey reveals that the DRAM market will remain extremely tight in the third quarter of 2026. However, weaker demand from consumer applications and the impact of a higher comparison base are expected to moderate contract price increases to 13-18% QoQ.

Demand for NAND Flash will continue to be driven primarily by AI inference and large-scale data center deployments. Yet, with contract prices already at record highs and consumer demand slowing, price tolerance among consumer customers has reached its limit. As a result, NAND Flash contract prices are projected to increase by 10-15% QoQ—a noticeably slower pace than in previous quarters.

NVIDIA GeForce RTX 5050 9 GB Edition Reportedly Cancelled

Earlier this year, we learned that NVIDIA might be planning to introduce a 9 GB edition of the GeForce RTX 5050 graphics card. However, later rumors suggested that the development was paused, and the latest reports claim that the project has been entirely canceled. According to MEGAsizeGPU, the GeForce RTX 5050 9 GB edition has been canceled because NVIDIA is currently relaunching its GeForce RTX 3060 12 GB edition GPU, which would compete with its own revived product. To avoid this overlap, the company has reportedly canceled the RTX 5050 9 GB edition launch. Initially, NVIDIA aimed to introduce this 9 GB version to address memory shortages in the lower-end segment. Instead of using four GDDR6 modules with 2 GB capacity each, NVIDIA planned to switch to three modules of GDDR7 with 3 GB capacity each, reducing the number of memory modules needed for this GPU.

For example, the current RTX 5050 uses 8 GB of 20 Gbps GDDR6 memory on a 128-bit bus, providing 320 GB/s of bandwidth. The 9 GB model was expected to use three modules of GDDR7 memory, each with 3 GB of capacity, resulting in a total of 9 GB across a 96-bit memory bus. While the narrower bus decreases the interface width, the switch to the new 28 Gbps GDDR7 memory would increase total memory bandwidth to 336 GB/s, a roughly 5% improvement, along with a 12.5% boost in VRAM capacity. Earlier leaks also claimed that NVIDIA was using the GB206 as a GPU base, while the older RTX 5050 8 GB with GDDR6 used the GB207 die. However, the core count remained at 2,560 CUDA cores. Since the GeForce RTX 3060 12 GB GPU is already on a path toward revival, launching this GPU wouldn't make sense.

HyperX Introduces First-Ever Valorant Gaming Laptop

Today, HP Inc. (NYSE: HPQ) announced the HyperX OMEN 16 VALORANT Limited Edition, a gaming laptop designed in collaboration with Riot Games that combines performance-driven hardware with a design of the most popular gaming titles, VALORANT. Built for players who demand speed, precision and personalization, the new laptop marks the latest milestone in HP's collaboration with Riot Games, following last year's OMEN 35L VALORANT Limited Edition desktop and the OMEN 16 League of Legends Limited Edition laptop. Together, these devices reflect a shared commitment to creating products that connect more deeply with fans of VALORANT and League of Legends.

HyperX gaming solutions are grounded in combining player-centric design with advanced engineering and intelligent software that can unlock greater performance. This laptop brings this approach to life with responsive performance, thoughtful customization and a design inspired by the VALORANT universe, helping players stay focused, react quickly and compete with confidence.

ASUS Republic of Gamers Announces ROG NUC 16

ASUS Republic of Gamers (ROG) today announced the ROG NUC 16, a compact gaming PC powered by up to an Intel Core Ultra "Arrow Lake-HX" processor and an NVIDIA GeForce RTX 5080 Laptop GPU. Featuring an upgraded thermal design and patented removable stand for vertical or horizontal placement, the ROG NUC 16 is built for gaming, creative pursuits, and AI workloads. Armed with the latest Intel Core Ultra 9 processor 290HX Plus, the ROG NUC 16 delivers improved gaming performance versus the previous-generation ROG NUC. It supports up to 128 GB of DDR5-6400 memory, ensuring smoother high-FPS gameplay and faster responsiveness.

Compact yet powerful, the ROG NUC 16 raises the bar with AI-enhanced performance. It features up to an NVIDIA GeForce RTX 5080 Laptop GPU and supports NVIDIA DLSS 4.5 with ML-based Super Resolution and Multi-frame generation for faster, smoother gameplay. Its updated Super Resolution transformer model delivers improved lighting, finer details, and clearer motion, benefiting real-time rendering, video editing, and up to 8K creative workloads. In addition, users can unleash creativity and generate images at unprecedented speed with NVIDIA Studio. For AAA gaming, DLSS 4.5 can reduce latency and generate up to five additional frames per rendered frame, enabling a more fluid and immersive experience. Combined with the Intel Core Ultra 9 290HX Plus processor, ROG NUC 16 delivers up to 2.3% better 3DMark performance than its predecessor.

NVIDIA Reportedly Prepares RTX 5090 Price Hike Amid Rising GDDR7 Costs

According to Chinese Board Channels, a reliable source for graphics card supply chain information, NVIDIA is reportedly preparing to increase the price of its GeForce RTX 5090 and RTX 5090D V2 GPUs. This will result in a $300 (about 2,000 RMB) increase for NVIDIA's add-in card (AIC) partners, who purchase these GPUs from NVIDIA. The change follows a significant price increase in GDDR7 memory, which NVIDIA has been absorbing but now plans to pass on to its AIC partners. The high demand for memory has depleted the supply of GDDR7 across the supply chain, with everything available being consumed and lead times now extending for weeks.

Interestingly, NVIDIA provides its AIC partners with a "GPU kit," which includes the GPU die itself, a GB202 in this case, and GDDR7 memory. This arrangement prevents AIC partners from having to source GDDR memory on their own, which would cause significant delays. Additionally, if memory makers sourced these modules themselves, they would have to make deals under unfavorable conditions, whereas NVIDIA can often secure a volume discount. However, due to the global shortage and insufficient memory chips, NVIDIA is forced to accept a higher GDDR7 price and pass it on to its AIC partners.

NVIDIA Officially Launches GeForce RTX 5070 Laptop GPU with 12 GB GDDR7 Memory

NVIDIA has officially launched its new GeForce RTX 5070 12 GB laptop edition GPU, featuring higher-capacity GDDR7 memory. This confirms earlier rumors about an upgraded memory configuration. In a quiet release, NVIDIA announced its decision to use 24 Gb (3 GB) GDDR7 memory modules, which offer a 50% increase in memory capacity compared to the current 16 Gb (2 GB) GDDR7 configurations. As demand for GPU memory remains high, NVIDIA can balance the supply of 16 Gb GDDR7 modules by utilizing a new batch of 24 Gb GDDR7 modules from partners like SK hynix, Samsung, and Micron. The company describes this move as a way to ensure a sufficient supply of 16 Gb GDDR7 memory for the remaining GeForce RTX 50-Series "Blackwell" GPUs, maintaining healthy supply levels. The new GPU SKU complements the existing RTX 5070 8 GB Laptop Edition model, providing gamers with more laptop configurations to choose from.
NVIDIADemand for GeForce RTX GPUs remains strong, and memory supply is constrained. In order to maximize memory availability, we are releasing the GeForce RTX 5070 Laptop GPU 12 GB configuration with 24 Gb G7 memory. This gives our partners access to an additional pool of memory to complement the 16 Gb G7 supply that currently ships with most GeForce GPUs. The 12 GB configuration will exist alongside the current 8 GB configuration, and allows our partners to bring a broader range of GeForce RTX 5070 laptops to consumers.

NVIDIA GeForce RTX 5060 and 5060 Ti Planned With 9 GB VRAM

It was recently revealed that NVIDIA plans to launch a version of the RTX 5050 GPU with 9 GB of VRAM—three 3 GB modules of GDDR7 over a 96-bit bus and 336 GB/s total memory bandwidth. Now, according to a new leak by Hakuitado on the Board Channels forum (via Gazlog), NVIDIA is planning to make the same move with the RTX 5060 and 5060 Ti in order to cater to budget consumers while avoiding high DRAM and BOM costs.

DRAM quantity aside, the move would also see NVIDIA decrease the bus width of the respective cards, going from 128-bit to 96-bit by using new 24 Gbit memory chips, resulting in an overall decrease in bandwidth and reduced memory performance. According to @harakuze5719 on X, the new 9 GB NVIDIA GeForce RTX 5060 and 5060 Ti GPUs are slated to launch sometime between May and June, with a Computex launch seemingly likely.
Return to Keyword Browsing
Nov 17th, 2026 20:51 CST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts