Stability AI, a maker of various generative AI models and the company behind text-to-image Stable Diffusion models, has released its latest Stable Diffusion 3 (SD3) Medium AI model. Running on two billion dense parameters, the SD3 Medium is the company's most advanced text-to-image model to date. It boasts features like generating highly realistic and detailed images across a wide range of styles and compositions. It demonstrates capabilities in handling intricate prompts that involve spatial reasoning, actions, and diverse artistic directions. The model's innovative architecture, including the 16-channel variational autoencoder (VAE), allows it to overcome common challenges faced by other models, such as accurately rendering realistic human faces and hands.

Additionally, it achieves exceptional text quality, with precise letter formation, kerning, and spacing, thanks to the Diffusion Transformer architecture. Notably, the model is resource-efficient, capable of running smoothly on consumer-grade GPUs without compromising performance due to its low VRAM footprint. Furthermore, it exhibits impressive fine-tuning abilities, allowing it to absorb and replicate nuanced details from small datasets, making it highly customizable for specific use cases that users may have. Being an open-weight model, it is available for download on HuggingFace, and it has libraries optimized for both NVIDIA's TensorRT (all modern NVIDIA GPUs) and AMD Radeon/Instinct GPUs.

A market research of AMD Socket AM5 motherboards sold in South Korea by Danawa, provide some interesting insights on how gamers approach the platform. This research is confined to Korea, but can be extrapolated to other similar markets. The research studies the chipset model, and form-factor of Socket AM5 motherboards sold in the market. The most interesting finding of the research is that the AMD B650 is by far the most popular chipset for the platform, dwarfing even the entry-level A620 chipset by a factor of 8. A staggering 80% of the Socket AM5 motherboards being sold are based on the B650.

It's important to note here, that this figure does not include the B650E, which is separately shown making up just 2% of the volumes. The B650 (non-E) has nearly all platform features, with motherboards based on the chipset providing at least one Gen 5 M.2 NVMe slot that doesn't eat into the lanes of the x16 PEG slot; and with the current generation of GPUs not featuring the PCIe Gen 5 host interface, customers seem more than happy with the Gen 4 x16 PEG slot provided by B650 motherboards. What's more, you get CPU overclocking and memory overclocking on this mid-range chipset, so it appeals to a very wide demographic. The B650E, on the other hand, provides a Gen 5 x16 PEG slot, and motherboards based on this chipset tend to offer premium I/O features, such as a high-end onboard audio solution, premium wireless networking, among others.

AMD late Tuesday released the latest version of its Chipset Software. This is an important piece of software that, besides providing drivers for the various onboard SoC interfaces of the processor and chipset, provides your Windows operating system with software-side processor power-management (PPM) awareness. Version 6.05.28.016 is the latest version of it, supporting AMD 300-series, 400-series, 500-series, and 600-series chipsets. Version 6.05.28.016 adds support for the new Windows 11 24H2 Update. Support is added for a new program (possibly the latest version of Ryzen Master). The release also adds a few unspecified bug-fixes.

DOWNLOAD: AMD Chipset Software 6.05.28.016The change-log follows.

AMD's upcoming Ryzen 9000 "Granite Ridge" desktop processors based on the "Zen 5" microarchitecture won't beat the Ryzen 7000X3D series at gaming workloads, said Donny Woligroski, the company's senior technical marketing manager, in an interview with Tom's Hardware. The new "Zen 5" chips, such as the Ryzen 7 9700X and Ryzen 9 9950X, will come close to the gaming performance of the 7800X3D and 7950X3D, but won't quite beat it. The new processors, however, will offer significant generational performance uplifts in productivity workloads, particularly multithreaded workloads that use vector extensions such as VNNI and AVX512. The Ryzen 7 7800X3D remains the fastest gaming desktop processor you can buy, it edges out even Intel's Core i9-14900KS, in our testing.

Given this, we expect the gaming performance of processors like the Ryzen 7 9700X and Ryzen 9 9950X to end up closer to those of the Intel Core i9-13900K or i9-14900K. Gamers with a 7000X3D series chip or even a 14th Gen Core i7 or Core i9 chip don't have much to look forward to. AMD confirmed that it's already working on a Ryzen 9000X3D series—that's "Zen 5" with 3D V-cache technology, and is sounds confident of holding on to the title of having the fastest gaming processors. This doesn't seem implausible.

AMD just announced the "This is why we Game" Q2-2024 game bundle. With a qualifying AMD Radeon RX 7800 XT or RX 7700 XT graphics card from a participating retailer, you can choose any two free games from the following: Avatar: Frontiers of Pandora, Starfield, Lies of P, and Company of Heroes 3. The bundle campaign period is from today (June 11), till July 20, 2024. You'll need to purchase a qualifying graphics card within this campaign period to be eligible. Once you've selected your two free games, you can redeem them (add them to your DRM platform account) before August 17, 2024. The Bundle is open in all countries except a handful mentioned in the terms & conditions page. Customers in Japan can only redeem one among the four games.

A curiously described graphics card was detected by Olrak29 as it was making it through international shipping. The shipment description for the card reads "GRAPHIC CARD NAVI48 G28201 DT XTX REVB-PRE-CORRELATION AO PLATSI TT(SAMSUNG)-Q2 2024-3A-102-G28201." This can be decoded as a graphics card with the board number "G28201," for the desktop platform. It features a maxed out version of the "Navi 48" silicon, and is based on the B revision of the PCB. It features Samsung-made memory chips, and is dated Q2-2024.

AMD is planning to retreat from the enthusiast segment of gaming graphics cards with the RDNA 4 generation. The company originally entered this segment with the RX 6800 series and RX 6900 series RDNA 2 generation, where it saw unexpected success with the crypto-mining market boom, besides being competitive with the RTX 3080 and RTX 3090. This bust by the time RDNA 3 and the RX 7900 series arrived, and the chip wasn't competitive with NVIDIA's top-end. Around this time, the AI acceleration boom squeezed foundry allocation of all major chipmakers, including AMD, making large chips based on the latest process nodes even less viable for a market such as enthusiast graphics—the company would rather make CDNA AI accelerators with its allocation. Given all this, the company's fastest GPUs from the RDNA 4 generation could be the ones that succeed the current RX 7800 XT and RX 7700 XT, so AMD could capture a slice of the performance segment.

An AMD Ryzen 5 9600X "Zen 5" processor engineering sample has been overclocked to 5.70 GHz on all cores, and put through the CPU-Z Benchmark. Here, the chip is found to score 871 points in the single-thread benchmark, and 7096 points in the multithreaded benchmark. The overclock to 5.70 GHz is significant, as this is the maximum boost frequency of the upcoming Ryzen 9 9950X flagship part. The single-thread benchmark highlights that "Zen 5" has a similar IPC to the "Raptor Cove" P-core of the Intel Core i9-14900K processor, while the 7096 points multithreaded score is higher than the that of the Ryzen 7 5800X "Zen 3," meaning that AMD is overcoming the deficit of two whole cores (33% of the core-count of the 9600X) with just IPC and faster memory. AMD is expected to launch the Ryzen 9000 series desktop processors in July 2024.

Arm CEO Rene Haas predicts that SoCs based on the Arm CPU machine architecture will beat x86 in the Windows PC space in the next 5 years (by 2029). Haas is bullish about the current crop of Arm SoCs striking the right balance of performance and power efficiency, along with just the right blend of on-chip acceleration for AI and graphics, to make serious gains in this market, which has traditionally been dominated by the x86 machine architecture, with chips from just two manufacturers—Intel and AMD. On the other hand, Arm has a vibrant ecosystem of SoC vendors. "Arm's market share in Windows - I think, truly, in the next five years, it could be better than 50%." Haas said, in an interview with Reuters.

Currently, Microsoft has an exclusive deal with Qualcomm to power Windows-on-Arm (WoA) Copilot+ AI PCs. Qualcomm's chip lineup spans the Snapdragon Elite X and Snapdragon Elite Plus. This exclusivity, however, could change, with a recent interview of Michael Dell and Jensen Huang hinting at NVIDIA working on a chip for the AI PC market. The writing is on the wall for Intel and AMD—they need to compete with Arm on its terms: to make leaner PC processors with the kinds of performance/Watt and chip costs that Arm SoCs offer to PC OEMs. Intel has taken a big step in this direction with its "Lunar Lake" processor, you can read all about the architecture here.

Handheld gaming devices are a dime a dozen these days and more and more companies are joining the fray on almost a weekly basis. At Computex, XPG was showing its upcoming handheld gaming device—currently known as the NIA—and it has several interesting features that most of their competitors haven't mentioned so far. The potentially most interesting feature that XPG has implemented is an LPCAMM2 module with support for up to 64 GB of LPDDR5x memory. XPG didn't list how much RAM the NIA will ship with, but 16 or 32 GB seems like the logical choices.

The device will be powered by AMD's Phoenix APU, but no details were given. XPG has implemented support for foveated rendering, which the company claims is an exclusive feature. This is courtesy of a front-facing camera with eye tracking, but it's unclear how exactly it'll work, since it won't be exactly the same as in a VR headset. The NIA will ship with an XPG Gammix S55 SSD, which is an M.2 2230 PCIe 4.0 NVMe drive with sizes of up to 2 TB. XPG also claims that the NIA is built for a "circular computing product lifecycle" whatever that means, but we're guessing it has something to do with using recycled materials and being recyclable. The screen size of the 1080p, 120 Hz display wasn't mentioned, but the screen can be tilted for better ergonomics and is supposed to deliver up to 500 nits brightness. The NIA also has a built-in kickstand.

We had a chance to briefly stop at Sapphire and it is one of the rare AMD GPU AIB partners that has something new to showcase at the Computex 2024. While it was announced earlier last month, we had a chance to check out the new Sapphire Radeon RX 7700 XT Pure Frostpunk 2 Edition graphics card, and it looks even better in person.

It could have something to do with the fact that we liked the original Frostpunk game and we can't wait to check out Frostpunk 2 when it launches on July 25th, but the card with white shroud and white fans with Frostpunk elements on its backplate certainly has its appeal. You also get a game code for the Deluxe Edition of the game in the box as well as some other goodies including custom keycaps and pin badges.In case you somehow missed it, the Radeon RX 7700 XT is based on the 5 nm Navi 32 GPU, packing 54 compute units for a total of 3,456 stream processors. AMD is targeting 1440p gaming with this card and it comes with 48 MB of Infinity Cache and 12 GB of 18 Gbps GDDR6 memory on a 192-bit memory interface. It needs two 8-pin PCIe power connectors, and includes two DisplayPort 2.1 and two HDMI 2.1 outputs.

In addition to the new PC cases and PSUs, ENERMAX also unveiled a couple of new and interesting AIO CPU coolers and fans at the Computex 2024 show, including the LIQTECH XTR AiO which can handle quite a high thermal load, the new AQUACore concept, which is actually a compact CPU cooler that integrates the pump and the radiator into a compact solution, and new Montage Flow fans with magnetic daisy-chaining.

The one that piqued our interest is definitely the LIQTECH XTR AIO liquid CPU cooler series, which can handle some impressive thermal loads. To be available in 240 mm, 280 mm, and 360 mm radiator sizes, the LIQTECH XTR can easily AMD Threadripper and Intel Xeon processors, offering 100 percent coverage and uses a powerful EF1 pump in combination with patented shunt-channel technology. According to Enermax and what we saw at the show, the smaller 240 mm can handle well over 500 W of thermal load, while the 360 mm one goes well over 900 W. The LIQTECH XTR also includes a digital built-in display on the pump/block unit, which shows CPU and GPU temperature, or fan RPM data.

ASRock Rack sells the entire stack of servers a data-center could possibly want, and at Computex 2024, the company showed us their servers meant for AI GPUs. The 6U8M-GENOA2, as its name suggests, is a 6U server based on 2P AMD EPYC 9004 series "Genoa" processors in the SP5 package. You can configure it with even the variants of "Genoa" that come with 3D V-cache, for superior compute performance from the large cache. Each of the two SP5 sockets is wired to 12 DDR5 RDIMM slots, for a total of 24 memory channels. The server supports eight AMD Instinct MI300X or MI325X AI GPUs, which it wires out using Infinity Fabric links and PCIe Gen 5 x16 individually. A 3 kW 80 Plus Titanium PSU keeps the server fed. There are vacant Gen 5 x16 slots left even after connecting the GPUs, so you could give it a DPU-based 40 GbE NIC.

The 6U8X-EGS2 B100 is a 6U AI GPU server modeled along the 6U8M-GENOA2, with a couple of big changes. To begin with, the EPYC "Genoa" chips make way for a 2P Intel Xeon Socket E (LGA4677) CPU setup, for 2P Xeon 5 "Emerald Rapids" processors. Each socket is wired to 16 DDR5 DIMM slots (the processor itself has 8-channel DDR5, but this is a 2 DIMM-per-channel setup). The server integrates an NVIDIA NVSwitch that wires out NVLinks to eight NVIDIA B100 "Blackwell" AI GPUs. The server features eight HHHL PCIe Gen 5 x16, and five FHHL PCIe Gen 5 x16 connectors. There are vacant x16 slots for your DPU/NIC, you can even use an AIC NVIDIA BlueField card. The same 3 kW PSU as the "Genoa" system is also featured here.

At Computex 2024, we went hands-on with the only custom-design AMD Radeon RX 7900 XTX graphics card to implement the 16-pin 12V-2x6 power connector. We've written quite a bit about this card, but weren't expecting it to be this long. This isn't just the only RX 7900 XTX with a 12V-2x6, but also the only air-cooled RX 7900 XTX that's strictly 2 slots-thick. ASRock made this card for graphics rendering farms, or AI development/inferencing builds, in which a GPU server would have 4-6 of these packed like sardines. The lateral blower helps ensure proper ventilation. The backplate is recessed to ensure better ventilation to the neighboring card.

The card sticks to AMD reference clock speeds of 2270 MHz Game clock, and 20 Gbps (GDDR6-effective) memory speed. ASRock also gave us a technical deep-dive into the card's design. For one, it's confirmed that the power connector is 12V-2x6 (H++) and not 12VHPWR. The cooling solution consists of a large copper vapor-chamber plate that makes contact with the GPU, memory, and VRM; conveying heat to an aluminium channel heatsink, which is ventilated by a high-speed lateral blower. The cooler shroud and backplate are both made of aluminium.

At Computex 2024, Colorful has followed the success of their popular COLORFIRE MEOW Series gaming desktops. The company has unleashed two fierce new gaming laptops - the COLORFIRE MEOW R15 and R16. These portable laptops are adorned with designs inspired by Bobi, COLORFIRE's beloved office cat. From paw print patterns to a sleek orange tabby color scheme, the laptops are littered with feline flair. Under the cat-inspired hood, the MEOW laptops pack a serious punch. They are equipped with the latest AMD Ryzen 8000 Series processors tailored for gaming, content creation, and entertainment. AMD Ryzen AI technology provides a boost to artificial intelligence capabilities. Both run on the AMD Ryzen 7 8845HS processor with eight cores, 16 threads, and a 5.1 GHz maximum boost clock. The Ryzen AI engine delivers up to 39 TOPS for accelerated AI performance. For graphics, the laptops feature up to an NVIDIA GeForce RTX 4070 GPU with 140 W of power.

The R15 has a 15.6-inch 2560x1440 IPS panel with 100% sRGB color and 165 Hz refresh rate. The R16 goes even bigger with a 16-inch 2560x1600 IPS display, 100% sRGB, and 240 Hz refresh. AMD FreeSync is there as well to ensure a tear-free experience. Colorful has outfitted the laptops with dual turbo fans, a 6-heatpipe solution, and performance control software to tame the heat from the powerful components. When it's time to pounce on the latest games, these MEOW laptops have the fierce cooling to keep their claws out.

TYAN, an industry leader in server platform design and a subsidiary of MiTAC Computing Technology Corporation, brings its latest AMD EPYC server platforms to the COMPUTEX 2024, Booth # M1120 in Taipei, Taiwan from June 4 to June 7.

"With the advanced capabilities of 4th Gen AMD EPYC Processors, TYAN's AMD EPYC server platforms deliver optimized performance for modern data centers and large-scale AI/HPC infrastructure, ensuring high energy efficiency and robust security," said Rick Hwang, President of MiTAC Computing Technology Corporation. "For the group of smaller businesses and dedicated hosters, TYAN offers AMD EPYC 4004 CPU-based servers that provide cost-effective, user-friendly solutions with enterprise-grade reliability, scalability, and security."

MSI, a leading brand in gaming, content creation, and business & productivity laptops, proudly announces the launch of several next-gen AI+ gaming and business productivity laptops featuring the latest Intel and AMD processors at COMPUTEX 2024. These laptops offer more than 100 TOPS of AI computing power and support more than 500 AI models run optimized on Intel Core Ultra processors, making it the most robust platform for AI PC development, with more AI models, frameworks, and runtimes enabled than any other processor vendor. When equipped with a GeForce RTX Laptop GPU, they offer up to 542 TOPS, delivering peak performance and enabling unique AI experiences.

Additionally, MSI unveiled the new Claw 8 AI+ Windows 11 gaming handheld device, powered by Intel Core Ultra processors (codenamed "Lunar Lake") and an 8-inch screen, providing a smoother and broader mobile gaming experience.

During Computex 2024, Alphacool presented its latest case lineup optimized for water cooling, in addition to more water cooling componentry. The Apex Pro Skeleton Carbon Case is a modular enclosure optimized for advanced water cooling setups. It is crafted from real carbon fiber tubes and reinforced with CNC-milled aluminium corners. It can be completely dismantled and reconfigured to suit the user's precise requirements. By utilizing a modular approach, users can change the system layout, optimize airflow, and achieve their unique cooling goals. Previously showcased at Computex 2023, the plan was for two SKU: Alphacool Apex Pro Skeleton Carbon Case and the Alphacool Apex Skeleton aluminium Case, the latter of which does not include a distribution plate or support for a vertical graphics card. The Apex Pro case with a custom distro plate will be available for $899, while the case-only solution will be available for $499.

At its Computex 2024 booth, AMD showed us their latest flagship desktop processor, the AMD Ryzen 9 9950X. This 16-core/32-thread beast is powered by the latest "Zen 5" microarchitecture, which promises a 16% IPC uplift over "Zen 4." AMD is also building the CCD (CPU complex dies) on the slightly upgraded 4 nm foundry node. The 9950X boosts up to 5.70 GHz, and AMD claims that it beats the Intel Core i9-14900K by near double-digit percentages in gaming, and significantly in multithreaded productivity. The chip is drop-in compatible with any AMD 600-series chipset motherboard with the latest BIOS. AMD plans to launch this processor in July. Given that Intel today announced that "Arrow Lake" will come out in Q4, the Ryzen 9000 series could enjoy free rein in the market for at 4 months.

AMD on Monday launched its Ryzen AI 300 line of mobile processors based on the 4 nm "Strix Point" monolithic silicon. This chip was described by AMD as having a maximum CPU core configuration of 12-core/24-thread, which would be a neat 50% increase in core-counts over the previous generation; but there's more to it. Although "Strix Point" implements "Zen 5," not all 12 CPU cores on the silicon are the regular variant of "Zen 5." The chip physically has four "Zen 5" cores, and eight "Zen 5c" compact cores. Nemez (GPUsAreMagic) attempted to annotate the "Strix Point" die based a high-resolution photo by System360Cheese from AMD's Computex keynote; and there are some interesting findings.

The annotation reveals that the four regular "Zen 5" cores, each with a 1 MB dedicated L2 cache, share a 16 MB L3 cache. The eight "Zen 5c" cores, on the other hand, appear to share a smaller 8 MB L3 cache, in what could be a separate CCX. They each have a 1 MB L2 cache, too. The "Zen 5c" cores have the same IPC as the "Zen 5" cores when measured with common INT and FP benchmarks that don't move a lot of data; however, it could lag behind in workloads with a lot of streaming data. What's more, the previous generation "Zen 4c" cores were traditionally limited to lower frequencies than regular "Zen 4" cores, as the physically compacted cores couldn't hold onto higher core voltages. If that's the case with "Zen 5c," then what we're really looking at with "Strix Point" is an interesting hybrid core setup with eight high-IPC efficiency cores.

ASUS Republic of Gamers (ROG) today announced the latest version of its critically acclaimed Zephyrus G16 gaming laptop, now featuring an AMD Ryzen AI 9 HX 370 processor. With a built-in NPU for AI-accelerated tasks and a dedicated NVIDIA GPU, the latest Zephyrus G16 stands ready for any scenario, from gaming to productivity and more—all in an ultra-sleek thin-and-light package.

Zephyrus enters the era of AI computing
We're entering a new era of computing, with artificial intelligence at its center—and ROG is charging ahead with the new Zephyrus G16, now a true AI PC thanks to its AMD Ryzen AI 9 HX 370 processor. With 12 cores, 24 threads, a built-in AMD Ryzen AI XDNA 2 NPU capable of 50 TOPS of AI performance, along with 31 TOPS from the CPU and its integrated Radeon 890M graphics, the new Zephyrus G16 stands ready for enhancing productivity in AI-enabled applications, including powerful Windows Copilot tools.

In addition to the new Zen 5 Ryzen 9000 series desktop CPUs and Ryzen AI 300 series mobile CPUs, as well as the new Ryzen 5000XT series AM4 socket desktop CPUs and updates to the AMD Instinct AI GPU roadmap, AMD rather silently announced the new Radeon PRO W7900 Dual Slot workstation graphics card at the Computex 2024. While not a completely new product, as it is just a model update of the currently available flagship Radeon PRO W7900 workstation graphics card, it is still a rather important update since AMD managed to squeeze it into a dual-slot design, which gives it support for multi-GPU setups.

As said, the AMD Radeon PRO W7900 Dual Slot still uses the same Navi 31 GPU with 96 Compute Units (CUs), 96 Ray Accelerators, 192 AI Accelerators, and 6144 Stream Processors, as well as 48 GB of GDDR6 ECC memory on a 384-bit memory interface, giving it maximum memory bandwidth of 864 GB/s. It still needs 2x8-pin PCIe power connectors and has a Total Board Power (TBP) of 295 W. The card still comes with three DisplayPort 2.1 and one Enhanced Mini DisplayPort 1.2 outputs. What makes the new Radeon PRO W7900 Dual Slot special is the fact that AMD managed to get it down to a dual-slot design, even with the same blower-fan cooler. Unfortunately, it is not clear if the fan or its profiles are different, but it does make it suitable to be used in multi-GPU configurations.

At Computex 2024, ASUS unveiled major updates to its popular laptop lineups, designed for the "Copilot+" era of AI computing. The first is the Zenbook S16 is a premium 16-inch laptop series powered by AMD's latest Ryzen AI 9 HX 370 processors with dedicated AI acceleration. Remarkably, ASUS has managed to pack this high-performance silicon into an ultra-portable 1.1 cm thin chassis weighing just 1.5 kg. The Zenbook S16 integrates AMD's new NPU capable of a 50 TOPS of AI compute for accelerating AI/ML workloads. The centerpiece is the laptop's stunning 16-inch 3K OLED display made with ASUS Lumina technology. It offers 100% vibrant DCI-P3 color gamut coverage, a blazing-fast 120 Hz refresh rate with 0.2 ms response time, and up to 600 nits brightness. ASUS paired this premium visual experience with a six-speaker audio system for an immersive multimedia experience.

German PC OEM Schenker, along with its two brands—XMG targeted at high-performance mobile workstations and gaming notebooks; and Tuxedo, targeting Linux-friendly notebooks; made a splash at the 2024 Computex. We visited their pullout booth. The EVO 14 is a 14-inch class performance notebook powered by choices of Intel Core Ultra 7 155H "Meteor Lake" or AMD Ryzen 7 8845HS "Hawk Point" mobile processors; an innovative new dual-fan cooling solution, with 65 W sustained power delivery, and an 80 Wh battery pack. The 14-inch display features a 16:10 aspect ratio, 400 nits brightness, and 3K resolution. Memory options go all the way up to 96 GB, and I/O includes either USB4 or Thunderbolt 4, depending on the hardware platform. The EVO 15 is almost identical in terms of specs, but with a larger 99.8 Wh battery, and a 15.3-inch 500 nits display, and a full-sized edge-to-edge keyboard.Update 07:03 UTC: We have some pricing and availability details from Schenker.

During Computex 2024, GIGABYTE unveiled its new "AI TOP" series designed to empower users to develop and run AI applications locally on their systems. The AI TOP lineup includes AI-optimized motherboards, graphics cards, and complete system solutions. The flagship motherboard is called TRX50 AI TOP, which boasts support for AMD's Ryzen Threadripper 7000 PRO and a regular series of CPUs. The flagship TRX50 AI TOP motherboard features a special VRM design with beefy heatsinks, four PCIe 5.0 x16 slots for quad-GPU setup, eight-channel DDR5 memory with room for eight DIMMs, and a few M.2 PCIe Gen 5 slots. Next in the AI TOP line is the GIGABYTE GeForce RTX 4070 Ti SUPER AI TOP edition. Formed as a blower-style cooler, the RTX 4070 Ti SUPER AI TOP is envisioned for tight spaces and parallel installation with other GPUs to accelerate local AI development and inference.

Supposedly, there will be more AI TOP motherboards and GPUs than what is showcased. GIGABYTE may have an AI TOP makeover for Intel's upcoming Z890 AORUS Xtreme, and there could be more GPUs in the future with the blower-style AI TOP design. The goal of AI TOP series is optimization for AI workloads, which require lots of GPUs and lots of memory, like the TRX50 AI TOP motherboard shows.

GIGABYTE in its Computex 2027 booth showcased a huge lineup of next-generation Socket LGA1851 motherboards based on the top Intel Z890 chipset, which are ready for Intel's Core Ultra "Arrow Lake-S" desktop processors. GIGABYTE has taped out the motherboard model names, so all mentions of Z890 in this article are based on our assumption that it's the name of the next-gen Intel chipset. These chips are expected to bring generational IPC increases from their "Lion Cove" P-cores, "Skymont" E-cores, a more complete PCIe Gen 5 I/O (including for the CPU-attached NVMe slots), and other innovations. If the socket looks similar to the LGA1700, it's because it's identical in physical dimensions, and you can use your LGA1700 cooler on the LGA1851, but the processors are not inter-compatible. The company also showcased a few AMD Socket AM5 motherboards based on the new AMD X870E chipset.

The first motherboard to catch our eye is the Z890 AORUS Tachyon. This board is geared for record-seeking CPU overclocking. The processor is wired to just two DDR5 memory slots (1 DIMM per channel, the best configuration for memory OC); and the CPU-attached NVMe slots being close to the socket, with a combined heatsink. The only expansion slots are a PCI-Express 5.0 x16, and what could be a Gen 4 x8. There are plenty of overclocker-friendly controls, voltage measurement points, diagnostic LEDs, and status displays, scattered all over the board.