NVIDIA's GeForce RTX 30-series and RTX 40-series graphics cards are based on the same dies as their professional-grade GPUs. This means the compute potential of consumer-oriented RTX GPUs is restricted by NVIDIA's firmware stack, but modders have managed to unlock the instruction issuing rate equivalent to their professional GPU counterparts. Starting with the GeForce RTX 30-series "Ampere," a researcher developed an unlock that effectively doubles the instruction issuing speed of FP/BF16 FMA into FP32 operations on GA102, GA103, GA104, and GA106 cards. As a result, cards like the GeForce RTX 3090 Ti experience up to 80% faster matrix multiplication in BF16, which is crucial for running nearly all neural networks. The unlock supports GA102, GA103, GA104, and GA106-based GeForce RTX graphics cards.

Next, we have the GeForce RTX 40-series "Ada Lovelace" with another project that has demonstrated a massive 2× speedup in FP16 and BF16 tensor throughput with FP32 accumulation. When the GeForce RTX 4090 was tested with FP16 tensor throughput and matrix accumulation, the GPU achieved 165.6 TeraFLOPS, while the unlock pushed that number to 331.6 TeraFLOPS. This is intriguing as these computational performance numbers are typically reserved for the higher-end professional segment like the NVIDIA RTX 6000 "Ada Lovelace." It seems NVIDIA artificially limited the AD102 silicon's performance in compute-sensitive matrix multiplication and accumulation, affecting the performance of running large language models. For this unlock, AD102, AD103, and AD106 are officially unlocked.

NVIDIA has officially confirmed that the company is working to bring DLSS 5 neural rendering to the previous-generation GeForce RTX 40-Series "Ada Lovelace." Previously, it was believed that DLSS 5 technology would be exclusive to the latest GeForce RTX 50-Series "Blackwell" and future models, without looking back. As NVIDIA continues to focus on hardware-software cooptimization, we now have official confirmation that the GeForce RTX 40-Series will also receive a DLSS 5 port. However, the launch of DLSS 5 on the GeForce RTX 40-Series is secondary, as NVIDIA is still preparing and optimizing performance for the GeForce RTX 50-Series to ensure that the model won't significantly impact the final game performance, despite reportedly being very compute-heavy.

NVIDIADLSS 5 is our most computationally demanding model to date. Since we initially announced it in March, we've achieved a 5X performance gain and there's more to come. Our current focus is on optimizing performance for the GeForce RTX 50 Series with model updates expected later this fall. Once RTX 50 Series performance is more fully tuned, we plan to work on expanding official support to the GeForce RTX 40 Series.

DLSS 5 leaked through an early-access build of NBA 2K27 last week, and since then, the modding community has been hard at work patching it into all sorts of different games. Modders on the RenoDX Discord have now pushed it into RTX 30-series "Ampere" GPUs, despite this generation having no official support for DLSS 5. The results, however, are less than stellar. On the RenoDX Discord, a user with an RTX 3070 laptop GPU running Kingdom Come: Deliverance II saw render latency jump from roughly 29 ms to over 3,300 ms with Neural Rendering enabled, resulting in well under 1 FPS.

Over on X, user @Flourek got it running on an RTX 3080, and it fared little better. It too, however, dropped from around 130 FPS to just 4 FPS in Deep Rock Galactic, while RTX 3050 and RTX 3060 Ti cards reportedly hovered near 1 FPS across Control, FiveM, and Kingdom Come: Deliverance II. Just a couple of days ago, modders got DLSS 5 running on RTX 40-series "Ada Lovelace" cards, and performance held up noticeably better. As we noted in our DLSS-NR deep dive, Ampere lacks native FP8 support, which the leaked DLSS 5 model apparently relies on, so the steep drop isn't surprising. Officially, DLSS 5 only supports RTX 50-series "Blackwell" GPUs, and there's no word about whether NVIDIA even plans to add support for RTX 40-series cards, let alone older ones.

The modding community has been hard at work ever since the untimely release of DLSS-NR, a precursor to DLSS 5. Now, modders have gotten NVIDIA's leaked DLSS 5 tool working on RTX 4000 series cards, even though the tool was only built for RTX 5000 Blackwell hardware. The DLL leaked earlier this week via an early-access build of NBA 2K27, and people on the RenoDX Discord quickly got it running in other games using ReShade and RenoDX.

As we noted in our DLSS-NR breakdown, the AI model runs on FP8, which Ada Lovelace GPUs support just fine, but the compiled binaries inside the file only targeted Blackwell's sm_120 architecture, with nothing built for Ampere or Ada. A modder going by "Uncle Burrito" has apparently fixed that by hunting down the incompatible binaries and swapping in ones built for Ada. Tom's Hardware confirmed the patch works on an RTX 4080, and said other developers in the same Discord are working on their own versions of the fix.

It seems that NVIDIA's removal of the hotspot temperature sensor from the GeForce RTX 50 series "Blackwell" GPUs is not permanent, as the sensor data can still be accessed and the actual sensor is physically present. However, this is only possible with NVIDIA's internal tool called Modular Diagnostic Software (MODS), which isn't available to the public. According to Brazilian repair specialist Paulo Gomes, NVIDIA's MODS tool can still access the hotspot sensor. Readers may recall that back in January 2025, when the GeForce RTX 5090 GPU was reviewed, it was confirmed that NVIDIA had indeed removed the hotspot sensor reading API from "Blackwell." However, the company has kept access to "GPU Temperature" and "Memory Temperature" features for measuring the overall GPU temperature and its memory, making up for the absence of the hotspot sensor by keeping other features available.

For those who want to access the hotspot sensor on NVIDIA's GeForce RTX 50 series, Paulo Gomes shows that it is possible through the use of MODS, which is an internal tool available only to NVIDIA employees in testing labs. Some builds have been circulating among repair technicians. The tool requires a bootable Linux drive and likely specific packages, making it difficult for the average enthusiast to set up. By connecting the tool from a remote server, the repair crew discovered that NVIDIA's thermal limit of 107°C had been reached five times in some hotspots on the GPU die, despite the average GPU temperature of the tested GIGABYTE GeForce RTX 5070 Ti being around 68°C.

NVIDIA has released its latest GeForce 610.62 WHQL game-ready drivers today, bringing support for the ultra-fast 6v6 shooter game "Empulse," which is scheduled for release on June 24, just a few days from now. NVIDIA is providing pre-release drivers to ensure gamers have day-one support when the game launches on Steam. The company also included a few bug fixes to improve the quality of use with GeForce RTX GPUs. For example, this driver release brings many fixes to World of Warcraft for improved stability during gameplay, as well as a remedy for visual corruption issues that occurred in Apex Legends at random times. Additionally, DLSS settings, which sometimes could gray out, have been fixed for regular contrast and access. Interestingly, this driver release also includes a crucial fix for the "Ada Lovelace" GeForce RTX 40 Series, which experienced frame pacing issues on some monitors when G-SYNC was enabled. General stability improvements have also been applied, making this driver release a worthwhile upgrade even for those not seeking day-one game support or using last-generation GeForce RTX GPUs.

DOWNLOAD: NVIDIA GeForce 610.62 WHQL

PCI-SIG has released a small update on its upcoming PCIe 8.0 standard, with the draft milestone reaching version 0.5. Perhaps the most intriguing aspect of this draft update is not the performance itself, but the exploration of a new connector technology to support this high-bandwidth protocol. Last year, we learned that PCI-SIG plans to implement a 256.0 GT/s raw bit rate and 1 TB/s of bidirectional bandwidth in the x16 lane configuration. We had assumed that the protocol would continue using the familiar connector technology seen in previous PCIe updates. However, it turns out that the current connector might be a limiting factor, prompting the search for a replacement for the traditional PCIe electrical connection.

The traditional PCIe connector is a copper-based link with up to 16 lanes connecting graphics cards to a slot. In a full x16 lane configuration, the PCIe generation supported by the motherboard provides the best performance, offering the maximum bandwidth the platform can deliver. However, with a 256 GT/s raw bit rate, the connector provides about 1 TB/s of bidirectional bandwidth, which is eight times faster than the current PCIe 5.0 platform used with modern GPUs and CPUs. This indicates that the current physical layer facilitating communication between a GPU and a motherboard is nearing saturation with the advent of PCIe 8.0, necessitating the consideration of an alternative connection method.

NVIDIA's GeForce RTX 3060 12 GB "Ampere" GPU, which is two generations old, is expected to make a comeback in June this year. Meanwhile, the rumored RTX 5050 9 GB edition is reportedly on hold. According to well-known hardware leaker MEGAsizeGPU on X, NVIDIA is pausing the transition from its 8 GB RTX 5050 "Blackwell" version to a 9 GB model due to the reintroduction of the GeForce RTX 3060 12 GB "Ampere" GPU. Since both of these GPUs compete in the budget segment, the company will reportedly only release the older GeForce RTX 3060 12 GB SKU with a 192-bit wide memory bus. For this, NVIDIA will once again use Samsung's 8 nm DUV node, as it has in the past. The entire NVIDIA "Ampere" architecture lineup was produced on the 8 nm DUV node, and its return after several years was unexpected. However, since NVIDIA has transitioned to TSMC for manufacturing its "Ada Lovelace" and latest "Blackwell" GPUs, becoming TSMC's largest customer using the 5 nm node, this move is intriguing.

The NVIDIA GeForce RTX 3060 features 3,584 CUDA cores and 12 GB of GDDR6 memory. In contrast, the GeForce RTX 5050 has newer CUDA cores on a smaller node with 2,560 cores on the GB207 die, but it has less memory, with only 9 GB of the rumored GDDR7. Since the resurrected GeForce RTX 3060 will use the older GDDR6 memory, sourcing GDDR6 may have been easier for NVIDIA, leaving the more expensive GDDR7 for its other GPUs.

Rowhammer attacks exploit vulnerabilities in DRAM hardware by causing targeted bit-flips, allowing attackers to bypass memory isolation and gain control over a device. These attacks were initially focused on CPUs and their associated DDR memory, such as DDR4. However, recent research indicates that NVIDIA GPUs are also vulnerable due to the fragile nature of the GDDR6 memory they use, which directly compromises the CPU host. Two independent research teams have discovered ways to exploit this decades-old memory vulnerability against modern graphics hardware, with trouble extending beyond the GPU itself. The "GDDRHammer" and "GeForge" groups have each developed functional exploits that use Rowhammer bit-flips in NVIDIA GPUs with GDDR6 memory to gain complete control over the host CPU's memory. This attack can perform bit-flips on some NVIDIA GPU models, ranging from the "Ampere" to "Ada Lovelace" families of cards.

An attacker who succeeds in this can read and write anything stored in the machine's main memory. Both teams have also introduced new Rowhammer techniques specifically designed for GPU architecture, achieving a significantly higher rate of bit-flips on GDDR6 memory than previous methods. The critical step in both exploit chains involves targeting the GPU's memory allocator, using controlled bit-flips to corrupt the GPU's page tables. Once these page tables are compromised, the attacker gains arbitrary read and write access to CPU memory, breaking down the security boundary between the graphics subsystem and the rest of the machine. The end result is a full system compromise, as the attacker can manipulate memory at will and gain root access, achieving total control without interacting with privileged software paths. The affected GPUs include the GeForce RTX 3060, which experienced 1,171 bit-flips, and the RTX 6000 "Ada" GPU, which saw 202 bit-flips from the attack.

NVIDIA's GeForce RTX 3060 is making a comeback, expected around mid-March. For this, NVIDIA will once again use Samsung's 8 nm DUV node, as it has in the past. This has been confirmed by the Korean media outlet Hankyung, which reports that Samsung is restarting its 8 nm node production to meet NVIDIA's needs. Originally, Samsung manufactured these GPUs back in 2021. The entire NVIDIA "Ampere" architecture lineup was produced on the 8 nm DUV node, and we didn't anticipate its return after several years. However, since NVIDIA has transitioned to TSMC for manufacturing its "Ada Lovelace" and latest "Blackwell" GPUs, and has become TSMC's largest customer, utilizing the 5 nm node, this move is intriguing.

We still lack concrete information about which version of the RTX 3060 will be reintroduced—whether it will be the original 12 GB model with a 192-bit wide memory bus or the newer 8 GB variant with a 128-bit bus. Additionally, the decision to use a two-generation-old GPU architecture in 2026 is puzzling, as the reason NVIDIA has chosen the RTX 3060 instead of a newer model like the RTX 4060 remains unclear. Speculatively, it could be because the RTX 4060 is based on the same NVIDIA 4N (5 nm-class) node at TSMC as the current RTX 5060, while the RTX 3060, along with the rest of the GeForce "Ampere" generation, is built on the Samsung 8N (8 nm DUV) foundry node, which would leave the 5 nm capacity for "Blackwell" and its enterprise variants. Finally, it is worth pointing out that when GPU IP design is done, it is usually hard-linked with the node it has been prepared for, so NVIDIA is sticking with Samsung again to avoid any potential upfront costs of adapting this GPU for a different node.

Zephyr, a Chinese manufacturer of custom NVIDIA and AMD graphics cards, has shared some insights into the development of their "Sakura Snow X" GeForce RTX 4070 Ti SUPER 16 GB model. Last week, a progress report was published via the company's official Bilibili blog. A lone shot of this upcoming SFF-format gaming product shows a familiar shroud design—last year, TechPowerUp covered Zephyr's similarly decorated "Sakura Snow X" GeForce RTX 4070 12 GB model. The NVIDIA board partner is nearing the finish line with their latest Mini-ITX project—they describe this new model being almost complete, due to it passing their own "35℃ constant temperature chamber test."

The still-in-progress "Sakura Snow X" GeForce RTX 4070 Ti SUPER candidate's power consumption reached Team Green's reference limit—the "full 285 W"—whilst meeting performance standards of the standard issue board design. Zephyr's diminutive cooling solution consists of a single fan and a contained heatsink module. Engineers tried out two different fan speeds—3000 and 3800 RPM—combined with three finstack material options. "Under normal open conditions" they found that their pure copper module performed best, albeit with a driving up of costs. The graphene-coated aluminium module recorded similarly results-wise when compared to a bare aluminium subject. Zephyr noted that the black finish—on the graphene-augmented variant—gave off the appearance of being a higher-end product.

Initial benchmarks shared on China's Weibo platform by INNO3D hinted that NVIDIA's upcoming GeForce RTX 5050 may not quite catch up to the GeForce RTX 4060 in raw performance. The leaked figures, which focused on a handful of 3DMark tests and a selection of game runs, showed the RTX 5050 lagging just a few percent behind its established last-gen mid-range sibling. While those early results did not cover a comprehensive range of titles, they suggested that the new card would fall slightly short of the RTX 4060's average frame rate and 1% low metrics when gaming at 1080p settings.

A more complete picture emerged from South Korea's Quasar Zone review of the Colorful iGame GeForce RTX 5050 Ultra OC White edition. In tests across fifteen popular 1080p games, the RTX 5050 delivered roughly 7% lower average frame rates and similar 1% low results compared to the RTX 4060. Even Intel's Arc B580 managed to edge it out by a small margin in those same trials. However, NVIDIA's Multi-Frame Generation options dramatically change the story by reconstructing additional frames on the fly. When these technologies are enabled, the RTX 5050 not only leaves older-generation cards well behind but also overtakes the higher-priced RTX 4060 Ti in several benchmarks. As we await more reviews to emerge, it will be interesting to see if the newest DLSS and MFG are sufficient for gamers to purchase the entry-level Blackwell GPU or opt for an older mid-range Ada Lovelace.

Instructions per clock is a metric used to define and compare CPU architecture performance usually. However, enthusiast colleagues at ComputerBase had an idea to test the IPC improvement in GPUs, comparing it across current and past generations. NVIDIA's Blackwell-based GeForce RTX 50 series faces off against the Ada Lovelace-based RTX 40 generation, while AMD's RDNA 4-powered Radeon RX 9000 lineup challenges the RDNA 3-based RX 7000 series. For NVIDIA, the test used RTX 5070 Ti and 4070 Ti SUPER, aligning ALU counts and clock speeds and treating memory bandwidth differences as negligible. For AMD, the test matched the RX 9060 XT to the RX 7600 XT, both featuring identical ALUs and GDDR6 memory. By closely matching shader counts and normalizing for clock variations, ComputerBase isolates IPC improvements from other hardware enhancements. In rasterized rendering tests across 19 popular titles, NVIDIA's Blackwell architecture delivered an average IPC advantage of just 1% over the older Ada Lovelace.

This difference could easily be attributed to normal benchmark variance. Ray tracing and path tracing benchmarks showed no significant IPC uplift, leaving the latest generation essentially on par with its predecessor when normalized for clock and unit count. AMD's RDNA 4, by contrast, exhibited a substantial IPC leap. Rasterized performance improved by around 20% compared to RDNA 3, while ray-traced workloads enjoyed a roughly 31% gain. Path tracing results were even more extreme, with RDNA 4 delivering nearly twice the FPS, a 100% increase over its predecessor. These findings suggest that NVIDIA's performance improvements primarily stem from higher clock speeds, increased execution unit counts, and enhanced features. AMD's RDNA 4 represents a significant architectural advance, marking its most notable IPC gain since the original RDNA launch.

Generative AI has reshaped how people create, imagine and interact with digital content. As AI models continue to grow in capability and complexity, they require more VRAM, or video random access memory. The base Stable Diffusion 3.5 Large model, for example, uses over 18 GB of VRAM - limiting the number of systems that can run it well. By applying quantization to the model, noncritical layers can be removed or run with lower precision. NVIDIA GeForce RTX 40 Series and the Ada Lovelace generation of NVIDIA RTX PRO GPUs support FP8 quantization to help run these quantized models, and the latest-generation NVIDIA Blackwell GPUs also add support for FP4.

NVIDIA collaborated with Stability AI to quantize its latest model, Stable Diffusion (SD) 3.5 Large, to FP8 - reducing VRAM consumption by 40%. Further optimizations to SD3.5 Large and Medium with the NVIDIA TensorRT software development kit (SDK) double performance. In addition, TensorRT has been reimagined for RTX AI PCs, combining its industry-leading performance with just-in-time (JIT), on-device engine building and an 8x smaller package size for seamless AI deployment to more than 100 million RTX AI PCs. TensorRT for RTX is now available as a standalone SDK for developers.

Perusers of the NVIDIA US Marketplace noticed a listing of an "Acme GeForce RTX 4040 8 GB BRICK Edition" product. Prior to a fresh removal, this mystery item was not in stock—reflecting the short supply of many GeForce RTX 50-series offerings. An advertised £$0.00" price indicates internal placeholder or jokey origins. After all, graphics card-related scams have involved the swiping of genuine articles—craftily replaced with similarly weighted substitutes. In some cases actual bricks, or—very recently—multiple cross-body backpacks stuffed into retail packages. According to news reports, NVIDIA's past-gen BRICK SKU is equipped with an impressive set of amusing features: "durable casing, passive cooling, absolute silence, and zero dependency on drivers." On a serious note, Team Green's desktop "Ada Lovelace" gaming card generation never dipped below the GeForce RTX 4060 tier. TechPowerUp's GPU database lists an unreleased GeForce RTX 4050 model—leakers believe that a direct successor will turn up in July.

Overclocking expert Roman "Der8auer" Hartung has managed to get his hands on a prototype of the NVIDIA TITAN ADA, a flagship design that never saw the light of day. Despite its absence from store shelves, the TITAN ADA prototype reveals a blend of workstation-level ambition and cutting-edge gaming power. Enthusiasts have long whispered about a true TITAN successor in the "Ada Lovelace" lineup, and now we finally have concrete evidence of what that card could have delivered. Inside this beast sits a fully enabled AD102 GPU, boasting all 144 streaming multiprocessors and delivering 18,432 CUDA cores, about 12 percent more than the retail RTX 4090. NVIDIA equipped the card with a staggering 48 GB of GDDR6X memory on a 384-bit bus to match this raw compute potential, twice the capacity of any other consumer Ada GPU. The prototype uses a large quad-slot, flow-through cooler in the classic beige TITAN color to keep everything cool.

Unlike conventional layouts, the TITAN ADA's PCB is split into three sections: a rotated main board flanked by a separate daughterboard for the PCIe interface. This unusual arrangement precedes the vertical board designs that would later appear on Founders Edition cards in the RTX 50 Series. Dual 16-pin power connectors suggest NVIDIA originally aimed for a total board power well above 600 watts, yet Der8auer's tests topped out near 450 watts, likely due to the prototype's early vBIOS and older driver builds. Benchmark results confirm the card's full AD102 configuration. In synthetic graphics tests, it ran roughly 15 percent ahead of the RTX 4090, and in real-world gaming scenarios, popular titles like Cyberpunk 2077 and Remnant 2 saw performance uplifts ranging from 10 to 22 percent. These figures place the TITAN ADA comfortably between the 4090 and the new RTX 5090 in both speed and efficiency.

AI-powered image generation has progressed at a remarkable pace—from early examples of models creating images of humans with too many fingers to now producing strikingly photorealistic visuals. Even with such leaps, one challenge remains: achieving creative control. Creating scenes using text has gotten easier, no longer requiring complex descriptions—and models have improved alignment to prompts. But describing finer details like composition, camera angles and object placement with text alone is hard, and making adjustments is even more complex.

Advanced workflows using ControlNets—tools that enhance image generation by providing greater control over the output—offer solutions, but their setup complexity limits broader accessibility. To help overcome these challenges and fast-track access to advanced AI capabilities, NVIDIA at the CES trade show earlier this year announced the NVIDIA AI Blueprint for 3D-guided generative AI for RTX PCs. This sample workflow includes everything needed to start generating images with full composition control. Users can download the new Blueprint today.

Compulab has updated its "ruggedised" Airtop3 compact form factor PC line with a new configuration that includes a pre-installed "Ada Lovelace" GeForce RTX 4060 8 GB discrete graphics card. Back in 2018, TechPowerUp's news section covered the Israeli firm's initiation of a crowdfunding campaign for their fanless Airtop2 Inferno Mini-PC. This second generation design launched with a desktop GeForce GTX 1080 "Pascal" card onboard. Compulab's current-gen SFF fanless IoT Edge server model was first revealed in 2019; debuting with passively cooled Intel Core i9-9900K (Coffee Lake Refresh) processors and Team Green's Quadro RTX 4000 (Turing) graphics cards. Going further back—to February 2018—the brand introduced its vanilla Airtop2 design.

The latest Airtop3 revision still utilizes an old LGA1151 socket platform; compatible with a small selection of Team Blue "Coffee Lake"—original and refreshed—CPUs. The best configuration can be equipped with a workstation grade Xeon E-2278GE processor. The cheapest option is outfitted with an entry level Celeron G4900T unit. As noted by VideoCardz, Compulab's starting price for an Airtop3 + GeForce RTX 4060 dGPU is $2780. A GPU-less setup costs $1790. Customers can pick between the GeForce RTX 4060 or an older "Ampere" RTX A2000 6 GB card. No matter the specification, CPU/APU and GPU aspects are passively cooled via sizeable copper plates.

More than 700 games and applications feature RTX technologies, and each week new games integrating NVIDIA DLSS, NVIDIA Reflex, and advanced ray-traced effects are released or announced, delivering the definitive PC experience for GeForce RTX players. This week, DLSS 4 with Multi Frame Generation is multiplying performance in Enotria: The Last Song, THE FINALS, and Wild Assault. And The Last of Us Part II Remastered is available now with DLSS Frame Generation, DLSS Super Resolution, and DLAA.

Wild Assault Launching April 11th, Featuring DLSS 4 With Multi Frame Generation
Combat Cat Studio's Wild Assault is a 20 vs. 20 third-person, Unreal Engine 5-powered, class-based PvP multiplayer shooter featuring a cast of anthropomorphic characters with unique animal-themed abilities. Battle across a variety of maps and modes in search of victory, and on GeForce RTX systems, activate DLSS and Reflex to accelerate performance and reduce PC latency.

Zephyr has presented a new Small Form Factor (SFF) graphics card design that houses previous-gen NVIDIA GPU hardware. The Chinese board partner showcased its GeForce RTX 4070-based "Sakura Snow X" via a 1-minute 42-second long teaser video; according to their bilibili channel this compact wonder is: "the world's first mass-produced CNC single-fan graphics card. A small space aesthetic benchmark—a balance of high performance and exquisite size." Zephyr's latest Mini-ITX offering seems to be a more premium—in terms of enclosure materials—alternative to last year's GeForce RTX 4070 12 GB "Sakura Blizzard" model—examples were placed next to each other in the AIB's demonstration video (aluminium versus plastic). This brand-new dual-slot entrant has arrived with a slightly larger cooling solution (see relevant screenshot below), and a fancier 105 mm airflow fan design—outfitted with more blades (11 vs. 9). VideoCardz has observed "Sakura Snow X" first batch listings on an undisclosed Chinese e-tail platform; launch pricing seems to be 4399 RMB (~$602 USD).

Unlike its pink-hued sibling, Zephyr's sober metal design integrates an I/O plate—giving off the impression of a unibody-esque setup. SFF enthusiasts will welcome this truly compact design, albeit with the disadvantage of playing host to old hat "Ada Lovelace" silicon. Throughout early 2025, Team Green and certain manufacturing partners have hyped up various "SFF-Ready" new-gen solutions. Last week, ZOTAC updated its "Blackwell" gaming portfolio with a dual-slot GeForce RTX 5070 Ti SOLID SFF card. This slimmed down triple-fan option is still a lengthy prospect (304.4 mm); thus quickly dismissed as unworthy of its moniker by compact graphics solution connoisseurs. Similarly, GIGABYTE sells 304 mm-long "SFF" variants—launched months ago in WINDFORCE and EAGLE guises.

Hello Civ fans, Update 1.1.0 is here—our first major update to Civilization VII! This update includes a mix of both paid and free content, with many of the free additions influenced by community feedback. For these extensive Update 1.1.0 notes, we've separated PC and Console into two separate sections so you can easily read them for your preferred platform. As part of these update notes, we're introducing a Feature Spotlight section, where the developers will dive deeper into new features or improvements being made. The Update Notes will cover all the addressed issues and improvements, including changes to both the base game and DLC. And lastly, for those who are excited about paid content additions, a Collection section will showcase the newest civs, leaders, and Wonders included in the latest paid Content Collection.

This update also brings a number of addressed issues and improvements specifically for console players. Some of these changes may already be available to PC players, but now all platforms are fully up-to-date. This also means cross-play between PC has been restored across PC, PlayStation, Xbox, and Switch, so you can once again enjoy cross-platform multiplayer between PC and these consoles with the latest version of the game. For a look into what else we're planning, take a look at our recently released Update Check-in detailing some of what you can expect in our next update, and some major features being scoped out for the future. As always, we're listening closely to your feedback, so please keep sharing your thoughts on the Steam Discussion forums or our official Civilization Discord Server.

Supply chain and board partner (AIB) insiders have once again signalled a murky future for Team Green's "Ada Lovelace" generation of gaming graphics cards—Chinese industry soothsayers believe that supplies of GeForce RTX 4060 GPUs will change significantly throughout February. A somewhat similar disclosure popped up online half-way through January—when members of the Board Channels discussion board predicted an end of the month stock depletion of NVIDIA GeForce RTX 4070 GPUs. Several web entities believe that NVIDIA is paving the way for a next wave of GeForce RTX 50-series "Blackwell" graphics cards.

Gory details appeared on Board Channels—yesterday morning's China market-focused bulletin stated: "supply of the main models of the RTX 4060 series will be greatly reduced from the first quarter of 2025, that is, from February 2025 in the domestic market, NVIDIA's supply of RTX4060 series GPUs will be greatly reduced, which is at least 60% less than the estimated Q4 of 2024." Team Green and its partners are reportedly working on a March launch window for GeForce RTX 5060 (non-Ti) and RTX 5060 Ti graphics card models—neatly aligning with the RTX 4060-related timeframes proposed by industry insiders. The Board Channels article added further clarification: "the number of GPUs that each core AIC brand manufacturer can get from NVIDIA will be greatly reduced."

Late last month, NVIDIA claimed that 16-pin power connector issues were a thing of the past. The controversial 12VHPWR connection standard has fueled many online debates—prompting investigations from several prominent press outlets. Following NVIDIA's latest "safety" declaration—likely by coincidence—PCM Hong Kong reported another melting incident, affecting two cables and a power supply unit. The publication's hardware reviewer was recently engaged in the "full-load" testing of GeForce RTX 5090D and RTX 5080 graphics cards. Last week's evaluation session was interrupted by notable test system instabilities—upon downing tools, the PCM staffer discovered that their 1200 W PSU had given up the ghost. Additionally, two 16-pin cables had melted at both ends—initial detective work pointed to a GeForce RTX 4090 sample card being the main culprit.

VideoCardz and UNIKO's Hardware kept close tabs on PCM's next steps—online interactions, over the past weekend, spurred a re-evaluation of circumstances. According to PCM's latest update, they noticed burn marks on the GeForce RTX 4090 test unit—the two GeForce RTX-50-series cards did not exhibit any physical damage. Post-analysis, the reviewer now suspects that an SSD failure could be the root cause. They were happy to report that all involved RTX cards have survived, and that their test platform has been re-equipped with 12V-2x6 cables. An amended VideoCardz article proposes that everything came down to a simple human error.

Supply chain insiders reckon that stock of NVIDIA's "Ada Lovelace" generation GeForce RTX 4070 GPU will be depleted by the end of this month. This revelation emerges on the cusp of Team Green's GeForce RTX 5000 series of "Blackwell" GPUs heading to market (on January 30). The popular Chinese hardware forum—Board Channels—is a reliable source of product "supply and demand" information. Industry insiders believe that Team Green's mid-tier SKU will be completely sold—by the closing of this month—across several unnamed regional markets. NVIDIA's incoming GeForce RTX 5070 SKU (baseline $549 MSRP) appears to be the natural alternative, given that GeForce RTX 4070 SUPER offerings are priced within the range of $550 to $600—according to market research performed by VideoCardz.

A board member disclosed details and prophesized changes up and down NVIDIA's current-gen product stack: "The inventory for NVIDIA RTX 4070 and higher models is expected to be completely cleared by January. Starting from February, major AIC brands are anticipated to have stock remaining only for the RTX 4060 Ti and RTX 4060 series, which still need to be digested. However, since NVIDIA's Q1 begins in February, these two models will essentially enter the final stock phase." VideoCardz anticipates a March launch window for the GeForce RTX 5060 series—this could be well-timed given circumstances surrounding Team Green's (alleged) limiting of GeForce RTX 4060 Ti GPU supplies and the insider's predicted cessation of RTX 4060 (non-Ti) production.

Jon Peddie Research (JPR) reports that shipments of integrated and standalone GPUs exceeded 251 million units in 2024, marking a 6% year-over-year rise. This growth continues to outpace the shipment figures for client CPUs, given that most desktop and laptop processors include built-in graphics, and that leading suppliers such as AMD and NVIDIA also provide tens of millions of discrete GPUs annually. Thanks to some earlier per-quarter data, we find that in the desktop segment, JPR shows that manufacturers shipped about 18.2 million discrete graphics cards in the first half of 2024—a 46% increase compared to the same period in 2023. However, shipments slowed in the third quarter, falling to 8.1 million units, down from 8.9 million units in Q3 2023.

Analysts partly attribute this dip to inventory adjustments at AMD, along with the end of product cycles for Ada Lovelace and RDNA 3 GPUs. Typically, the fourth quarter sees a boost in discrete GPU purchases as gamers gear up for new software releases. Yet it is not entirely clear whether that trend held through late 2024. Early indications suggest that total graphics card shipments for the year lightly exceed the totals from 2023, thanks primarily to strong demand in the first half. We still need data from Q4 of 2024 to see the trend in its final months of the year, despite knowing that the year-over-year growth is 6%. Nonetheless, current levels appear unlikely to approach the elevated peaks observed in 2021 or 2022.