AMD has launched a new open-source project called, GAIA (pronounced /ˈɡaɪ.ə/), an awesome application that leverages the power of Ryzen AI Neural Processing Unit (NPU) to run private and local large language models (LLMs). In this blog, we'll dive into the features and benefits of GAIA, while introducing how you can take advantage of GAIA's open-source project to adopt into your own applications.

Introduction to GAIA
GAIA is a generative AI application designed to run local, private LLMs on Windows PCs and is optimized for AMD Ryzen AI hardware (AMD Ryzen AI 300 Series Processors). This integration allows for faster, more efficient processing - i.e. lower power- while keeping your data local and secure. On Ryzen AI PCs, GAIA interacts with the NPU and iGPU to run models seamlessly by using the open-source Lemonade (LLM-Aid) SDK from ONNX TurnkeyML for LLM inference. GAIA supports a variety of local LLMs optimized to run on Ryzen AI PCs. Popular models like Llama and Phi derivatives can be tailored for different use cases, such as Q&A, summarization, and complex reasoning tasks.

AMD's latest flagship APU, the Ryzen AI MAX+ 395 "Strix Halo," demonstrates some impressive performance advantages over Intel's "Lunar Lake" processors in large language model (LLM) inference workloads, according to recent benchmarks on AMD's blog. Featuring 16 Zen 5 CPU cores, 40 RDNA 3.5 compute units, and over 50 AI TOPS via its XDNA 2 NPU, the processor achieves up to 12.2x faster response times than Intel's Core Ultra 258V in specific LLM scenarios. Notably, Intel's Lunar Lake has four E-cores and four P-cores, which in total is half of the Ryzen AI MAX+ 395 CPU core count, but the performance difference is much more pronounced than the 2x core gap. The performance delta becomes even more notable with model complexity, particularly with 14-billion parameter models approaching the limit of what standard 32 GB laptops can handle.

In LM Studio benchmarks using an ASUS ROG Flow Z13 with 64 GB unified memory, the integrated Radeon 8060S GPU delivered 2.2x higher token throughput than Intel's Arc 140V across various model architectures. Time-to-first-token metrics revealed a 4x advantage in smaller models like Llama 3.2 3B Instruct, expanding to 9.1x with 7-8B parameter models such as DeepSeek R1 Distill variants. AMD's architecture particularly excels in multimodal vision tasks, where the Ryzen AI MAX+ 395 processed complex visual inputs up to 7x faster in IBM Granite Vision 3.2 3B and 6x faster in Google Gemma 3 12B compared to Intel's offering. The platform's support for AMD Variable Graphics Memory allows allocating up to 96 GB as VRAM from systems equipped with 128 GB unified memory, enabling the deployment of state-of-the-art models like Google Gemma 3 27B Vision. The processor's performance advantages extend to practical AI applications, including medical image analysis and coding assistance via higher-precision 6-bit quantization in the DeepSeek R1 Distill Qwen 32B model.

We dedicated a lot of our launch presentation of Framework Desktop to the Ryzen AI Max processor it uses, and for a good reason. These truly unique, ultra-high-performance parts are the culmination of decades of technology and architecture investments that AMD has made, going all the way back to their acquisition of ATI in 2006. For our first technical deep dive on Framework Desktop, we're going to go even deeper into Ryzen AI Max and what makes it a killer processor for gaming, workstation, and AI workloads.

What makes Ryzen AI Max special is a combination of three elements: full desktop-class Zen 5 CPU cores, a massive 40-CU Radeon RDNA 3.5 GPU, and a giant 256-bit LPDDR5x memory bus to feed the two, supporting up to 128 GB of memory. Chips and Cheese did an excellent technical overview of the processor with AMD that goes even deeper on this, and we'll pull out some of the highlights along with our own insights. We'll start with the CPUs. Ryzen AI Max supports up to 16 CPU cores split across two 4 nm FinFET dies that AMD calls CCDs. These dies are connected together using an extremely wide, low power, low latency bus across the package substrate. The CPUs are full Zen 5 cores with 512-bit FPUs and support for AVX-512, a vector processing instruction set otherwise only available on Intel's top end server CPUs. We're excited for you to see the multicore performance numbers these CPUs can do in our upcoming press review cycle!

It seems that Sapphire is making a return to the Mini-PC consumer market as ComputerBase discovered during Embedded World 2025 event. There, Sapphire showcased engineering samples of its new Edge AI mini-PC family. These compact computing solutions are based on the latest AMD Ryzen AI 300 series processors.. The two models in this lineup—the Edge AI 340 and 350—feature AMD Ryzen AI 5 340 and Ryzen AI 7 350 processors respectively, with the former offering 16 GB of RAM and the latter providing 32 GB, both supporting impressive 5,600 MT/s memory speeds across two SO-DIMM slots. A more powerful model featuring AMD Ryzen AI 9 HX 370 will also be available.

Even measuring just 117 × 111 × 30 mm in size (the power supply is just a regular external adapter), the Sapphire Edge AI series features a wide range of connections. They boast two HDMI 2.1 ports, two USB4.0 ports, 2.5 GbE LAN, Wi-Fi with Bluetooth, and two extra USB ports. As for storage, there's a regular 2280 M.2 slot for SSDs, plus another 2242 slot. Accessing internal components is easy; no tools are needed, as Sapphire makes use of a magnetic case-cover. This includes access to the SO-DIMM slots and storage areas. Sapphire says these mini-PCs will hit stores worldwide by late April (no word about pricing yet), however, some regions might get different setups or bare-bones versions without pre-installed RAM and storage.

Minisforum is proud to unveil AI X1 Pro, the world's first Copilot-empowered AI mini PC, setting a new standard in low power efficiency and redefining performance. Powered by the cutting-edge AMD Ryzen AI 9 HX 370 processor, the AI X1 Pro delivers next-level AI technology, supercharging multitasking, boosting productivity, and enhancing teamwork like never before. With performance up to 45% faster than competitors, this mini PC is designed to meet the demands of professionals, creators, and gamers alike.

Unmatched Gaming and Creativity
Equipped with the powerful AMD Radeon 890M processor, AI X1 Pro transforms your gaming experience. Dive into AAA titles with smooth, breathtaking visuals and zero lag. Every battle and adventure comes to life in stunning detail, delivering pure excitement. For creators, the AI X1 Pro is optimized for AI workloads, featuring total 80 TOPS NPU for all-local AI processing. Streamline your daily tasks, enhance creativity, and save valuable time with unparalleled convenience.

At MWC 2025, Lenovo unveils its latest portfolio of AI-powered business devices, featuring next-generation ThinkPad and ThinkBook laptops, expanded software and recent ThinkShield security solutions, and showcases visionary proof-of-concept innovations. Designed to enhance productivity, personalization, and business protection, these new devices integrate AI-driven computing, flexible form factors, and enterprise security solutions to meet the evolving demands of professionals and hybrid workers.

"AI is fundamentally transforming how businesses operate, and at Lenovo, we are committed to delivering smarter, more secure, and more adaptable solutions that empower professionals in today's fast-evolving workplace. Our latest ThinkPad and ThinkBook innovations leverage AI to enhance productivity, streamline IT management, and provide more secure and seamless hybrid work experiences," said Eric Yu, SVP of SMB and Commercial Product Center, Lenovo Intelligent Devices Group. "The ThinkBook codename Flip AI PC Concept exemplifies our vision for the future—where AI-powered devices drive efficiency, personalization, and collaboration like never before. With our expanding portfolio of AI-integrated business devices and intelligent IT solutions, Lenovo is helping organizations to harness the power of AI in an ever-changing world."

ASUS today announced ExpertCenter PN54, a high-performance Copilot+ mini PC powered by AMD Ryzen AI 300 Series processors and AMD Radeon graphics. ExpertCenter PN54 offers extensive connectivity, including WiFi 7 and Bluetooth 5.4, and is able to support up to four 4K displays. This mini PC enables retailers and business to maintain their competitive edge alike: it's well-equipped to handle data-intensive workloads, AI-enhanced applications, and edge data processing. PN54 boasts more I/O ports than other mini PCs, allowing retailers to connect to multiple devices for field deployment or in limited-space environments.

First Copilot+ mini PC by ASUS built on AMD architecture
At the heart of ExpertCenter PN54 is the latest AMD Ryzen AI 300 Series processor that delivers over 50% more on-chip memory for enhanced performance. Built on the cutting-edge AMD Zen 5 cores previously only available in desktop CPUs, this latest processor features eight cores of processing power and a 5 GHz boost frequency. And with the advanced AMD XDNA 2 NPU Architecture, ExpertCenter PN54 handles AI-powered content creation, code compilation, data analysis, meetings, and other tasks seamlessly.

Shahram Mokhtari and Elizabeth Chamberlain—members of the iFixit Teardown Team—spent hands-on time with Framework's freshly introduced 4.5 liter Mini-ITX "Desktop" PC system. Official press material revealed cooling solution partnerships with Cooler Master and Noctua, but only a minority of "2nd Gen event" attendees were allowed to handle these pre-release modular parts. iFixit employees did not perform a full evaluation of Framework's new desktop model, since they were dealing with a prototype unit. A "repairability score" will be awarded once finalized hardware is delivered to iFixit's base of operations. In the meantime, their video team was hosted at Framework's Northern California office.

According to a follow-up report, Mokhtari and Chamberlain enjoyed their visit: "it's teardown time. Framework has been a beacon of repairability in the laptop space, and now they're bringing that ethos to desktops...Taking this thing apart was exactly as easy as we've come to expect from Framework. They brought us to their HQ to rip into it, and from the very first step, it was clear: this desktop was designed to be opened." Potential buyers—of Framework Desktop—are faced with many configurations, but a crucial choice will focus on available APU options. The highest-end builds will feature AMD's 16-core Ryzen AI Max+ 395 "Strix Halo" processor—iFixit's teardown did not reveal any major revelations in terms of the APU's physical appearance. Even Framework's own press release contains an exposed shot—hardcore processor design enthusiasts are better catered to with a more in-depth analysis of "Strix Halo."

GSMA MWC Barcelona, runs from March 3 to 6, 2025 at the Fira Barcelona Gran Via in Barcelona, Spain. AMD is proud to participate in forward-thinking discussions and demos around AI, edge and cloud computing, the long-term revolutionary potential of moonshot technologies like quantum processing, and more. Check out the AMD hospitality suite in Hall 2 (Stand 2M61) and explore our demos and system design wins. Attendees are welcome to stop by informally or schedule a time slot with us.

As modern networks evolve, high-performance computing, energy efficiency, and AI acceleration are becoming just as critical as connectivity itself. AMD is at the forefront of this transformation, delivering solutions that power next-generation cloud, AI, and networking infrastructure. Our demos this year showcase AMD EPYC, AMD Instinct, and AMD Ryzen AI processors, as well as AMD Versal adaptive SoC and Zynq UltraScale+ RFSoC devices.

Framework has finally introduced its next-generation Framework Laptop 13, now powered by the extremely potent Ryzen AI 300 "Strix Point" APUs. The product is already available for pre-order on Framework's website, with prices starting from $899 for the Do-It-Yourself variant, and $1,099 for the fully assembled variant. From the outside, the design of the product has been left mostly unchanged, which may appear somewhat disappointing at first, although an unaltered design likely indicates compatibility of components between the two laptops, which is undoubtedly one of the primary selling points for the Framework Laptop.

As mentioned, the biggest upgrade that the new Framework Laptop brings to the table is the new selection of processors, with the Ryzen AI 9 HX 370 APU sitting at the highest-end. Unsurprisingly, the Strix Point APUs allow for excellent performance improvements to both CPU and GPU side of things. With 12 cores (4 Zen 5 + 8 Zen 5c) and 24 threads, the highest-end Ryzen AI 9 HX 370 APU performs admirably well in benchmarks as well as real-life workloads. The Radeon 890M iGPU is among the fastest available on the market, trading blows with the Arc 140T iGPU in synthetic benchmarks. Of course, the 50 TOPS NPU allows for CoPilot functionality, for those who care. The Windows variant ships with a dedicated CoPilot key as well, while the DIY variant does not.

MSI, the world-leading gaming & creator laptop brand, today announced its groundbreaking RTX 50 Series laptops at MSIology: Dragonforged Dominance Launch Event - a new lineup inspired by the ancient Norse myth of Yggdrasil. Embracing the themes of renewal and resilience, MSI's innovative devices integrate three core principles: innovative technology, luxurious aesthetics, and extreme performance.

Dragonforged Dominance Launch Event
"Much like the mythic World Tree that connects the nine realms, our new laptops are designed to meet diverse user expectations—from immersive gaming to high-end professional work" said Steven Yang, MSI Notebook Regional Sales & Marketing Manager.

Today, we introduced the Framework Desktop, a tiny 4.5L Mini-ITX desktop powered by AMD's massive new Ryzen AI Max processors. Pre-orders are open now, with first shipments in early Q3 2025. When AMD shared the Ryzen AI Max with us, we immediately knew we had to use it. It has up to 16 CPU cores at 5.1 GHz boost clock, discrete-level Radeon 8060S graphics, and support for up to an insane 128 GB of unified LPDDR5x. That enables 1440p or higher gaming on the heaviest titles, big creative and workstation workloads, and true local AI use cases. This is an absolute monster of a processor, and we shifted our roadmap a year ago to make space for it. In a desktop form factor, we get to unlock every bit of its performance with 120 W sustained power and 140 W boost while staying quiet and cool.

You may still be wondering, why does Framework need to build a desktop? Aren't desktops already modular and upgradeable? They are. In fact, the desktop PC ethos is part of what inspired the Framework Laptop to begin with. The desktop world is amazing. There is a broad, long-lived, interoperable ecosystem with hundreds of brands and hundreds of millions of consumers participating. You can build, upgrade, repair, and personalize to the limits of your imagination (and budget, and desk space), and share your amazing creations with all of the other true believers. We want to make this space as accessible as we possibly can by building a desktop that is simultaneously small and simple and incredibly powerful and customizable. Everyone should have the opportunity to experience the culture around PCs and PC gaming first-hand.

Navigating AMD's various modern processor model naming schemes is tricky business, and another layer of complexity has been added this week; with newly revealed "Strix Point" and "Krackan Point" CPUs. Three previously unannounced SKUs have appeared on AMD's Chinese website: Ryzen AI 9 H 365, Ryzen AI 7 H 350, and Ryzen AI 5 H 340. At first glance, these models codes seem to be familiar—after a double take, we see a small difference in nomenclature. The addition of a middle-placed/detached "H" has press outlets and hardware enthusiasts scratching their collective heads. After discovering Team Red's Ryzen AI 9 H 365 APU listing, Lonely City Hardware posted a humorous observation on social media: "for the Chinese market. No one can remember the full name."

Frustratingly, Western search engines (at the time of writing) just point you to the non-H equivalents. The "H" designation denotes Chinese market exclusivity; TechPowerUp has covered previous-generation examples in the recent past. When comparing technical details and specification sheets to Western equivalents, VideoCardz noted that there were no apparent differences—platform and packaging are the same (FP8). A cross-reference—of clock speeds, thermal ratings, and core architecture (Zen 5/Zen 5C)—points to spec parity across East and West variants.

It's that time again! 3DExperience World 2025 kicks off on February 23 and runs through February 26 at the George R. Brown Convention Center in Houston, Texas. The show is hosted by Dassault Systèmes and highlights annual advances and improvements throughout its product ecosystem. It's a great opportunity to meet the engineers, students, and industry professionals who use SolidWorks and other Dassault Systèmes applications across browsers, local workstations, and the cloud.

One of the best parts of the event for me is showcasing how advances in silicon engineering can lead to transformational products - systems that offer performance, features, and efficiency that wasn't possible before. In 2024, the AMD Ryzen Threadripper PRO 7000 WX-Series processor stole the proverbial show with its excellent single-thread performance, support for multi-GPU configurations for AI training, and up to 96 cores and 2T B of memory for the largest and most demanding projects. This year, AMD has complemented these full-size tower systems with compact and mobile workstations based on the new AMD Ryzen AI Max PRO Series processors. Drop by booth #919 and see the array of systems and demos on exhibit.

AMD's "Strix Halo" APU, marketed as Ryzen AI Max+, has just been exposed in die-shot analysis. Confirming the processor's triple-die architecture, the package showcases a total silicon footprint of 441.72 mm² that integrates advanced CPU, GPU, and AI acceleration capabilities within a single package. The processor's architecture centers on two 67.07 mm² CPU CCDs, each housing eight Zen 5 cores with a dedicated 8 MB L2 cache. A substantial 307.58 mm² I/O complements these die that houses an RDNA 3.5-based integrated GPU featuring 40 CUs and AMD's XDNA 2 NPU. The memory subsystem demonstrates a 256-bit LPDDR5X interface capable of delivering 256 GB/s bandwidth, supported by 32 MB of strategically placed Last Level Cache to optimize data throughput.

The die shots reveal notable optimizations for mobile deployment, including shortened die-to-die interfaces that reduce the interconnect distance by 2 mm compared to desktop implementations. Some through-silicon via structures are present, which suggest potential compatibility with AMD's 3D V-Cache technology, though the company has not officially confirmed plans for such implementations. The I/O die integrates comprehensive connectivity options, including PCIe 4.0 x16 lanes and USB4 support, while also housing dedicated media engines with full AV1 codec support. Initial deployments of the Strix Halo APU will commence with the ASUS ROG Flow Z13 launch on February 25, marking the beginning of what AMD anticipates will be broad adoption across premium mobile computing platforms.

ASUS Republic of Gamers (ROG) announced that the 2025 ROG Flow Z13 is now available for pre-order. This versatile gaming 2-in-1 can feature up to AMD's newest AMD Ryzen AI Max+ 395 Processor with Radeon 8060S Graphics and a unified memory structure, allowing for incredible performance and power efficiency. A new stainless steel and copper vapor chamber, larger intake vents, and 2nd Gen Arc Flow Fans offer 70% more airflow for quiet and efficient cooling.

This 13-inch tablet boasts a stunning ROG Nebula Display, a 2.5K resolution 180 Hz touchscreen with 500 nits of peak brightness, and Corning Gorilla Glass 5 protection. The Flow Z13 now also features a larger 70Wh battery, a larger touchpad and keycaps, and a convenient Command Center button for quick access to vital system functions. With dual USB-C ports, both of which support USB4 and power delivery, as well as a dedicated HDMI 2.1 port, the Flow Z13 lets gamers leave their dongles at home.

Yesterday, the ASUS Chinese office announced a special event—on February 25—dedicated to launching a next-gen AMD APU-powered premium notebook model: "ROG Magic X (or Illusion X) is the first to be equipped with the Ryzen AI MAX+ three-in-one chip, which can efficiently coordinate multiple modes, provide combat power and computing power on demand, and can handle e-sports, creation and AI with one chip!" The manufacturer's Weibo post has generated plenty of buzz; industry insiders reckon that reviews could be published today (February 18)—HXL/9550pro informed VideoCardz with a not so cryptic message: "STX-Halo NDA: Feb 18th 2025."

Western press outlets point out that the ROG Magic X is a local variant of the familiar ROG Flow Z13 design; a 2025 refresh brings in AMD's much anticipated "Strix Halo" APU design. Team Red-authored marketing material and pre-release evaluation leaks have hinted about impressive integrated graphics solution performance; equalling or even exceeding that of previous-gen dGPUs. Well-known North American hardware review outlets have dropped hints (NDA permitting) about AMD's Ryzen Al Max+ 395 and Max 390 processors. Hardware Canucks could barely contain their excitement regarding the potent Zen 4 and RDNA 3.5 combo package; to the point of wish listing a potential direct successor: "Strix Halo is one of the most exciting things launched into the PC space in the last half decade. Full stop...AMD can't keep this as a one-off. If it's followed up with Zen 6 and RDNA 4 next year...watch out." Naturally, Team Red's cutting-edge mobile CPU technology is arriving in devices with high asking prices. The aforementioned ROG Flow Z13 2025 model—configured with top specs—is priced at $2699. Notebookcheck reckons that ASUS has tacked on an extra $500, since an announcement of initial pricing at CES 2025.

ASUS's Republic of Gamers China account on Weibo has teased the ROG Magic X mobile device that combines laptop/tablet form with a detachable keyboard. Inside, the device is powered by AMD Ryzen AI MAX+ SoC, which ASUS called a "three-in-one" chip, mainly due to its CPU, NPU, and iGPU combination. One possible SKU for ROG Magic X is AMD's top-end Ryzen AI MAX+ 395 processor. Carrying 16 "Zen 5" cores and 32 threads, the chip is designed for AI-enhanced laptops with 126 combined TOPS of AI processing power. The Ryzen AI MAX+ 395 features 64 MB of L3 cache and operates at a base clock of 3 GHz, with boost capabilities up to 5.1 GHz, depending on workload conditions. Manufactured on TSMC's 4 nm process node, the processor maintains a modest 55 W TDP, suitable for high-performance mobile systems. The chip includes support for ECC memory and PCIe Gen 5. It integrates the Radeon 8060S solution based on RDNA 3.5 architecture for graphics.

We are yet to see more details about the ROG Magic X, but with the arrival of AMD Ryzen AI MAX+, we assume this machine will result in a powerful gaming device for users on the go. More details are expected on February 25, when ASUS plans to showcase it. Pricing and availability are also expected to follow soon after.

AI PC capabilities have evolved rapidly in the two years since AMD introduced the first x86 AI PC CPUs at CES 2023. New neural processing units have debuted, pushing available performance from a peak of 10 AI TOPS at the launch of the AMD Ryzen 7 7840U processor to peak 50+ TOPS on the latest AMD Ryzen AI Max PRO 300 Series processors. A wide range of software and hardware companies have announced various AI development plans or brought AI-infused products to market, while major operating system vendors like Microsoft are actively working to integrate AI into the operating system via its Copilot+ PC capabilities. AMD is on the forefront of those efforts and is working closely with Microsoft to deliver Copilot+ for Ryzen AI and Ryzen AI PRO PCs.

In the report "The Year of the AI PC is 2025," Forrester lays out its argument for why this year is likely to bring significant changes for AI PCs. Forrester defines the term "AI PC" to mean any system "embedded with an AI chip and algorithms specifically designed to improve the experience of AI workloads across the computer processing unit (CPU), graphics processing unit (GPU), and neural processing unit (NPU)." This includes AMD products, as well as competing products made by both x86 and non-x86 CPU manufacturers. 2025 represents a turning point for these efforts, both in terms of hardware and software, and this Forrester report is an excellent deep dive into why AI PCs represent the future for enterprise computing.

At some point this week, HP's North American online store was updated with new high-end EliteBooks that feature AMD Strix Point APUs. Three models appear to support up to 128 GB of LPDDR5X-8533 memory—these curious entries were highlighted by tech enthusiast Hoang Anh Phu (AnhPhuH). The advertised maximum 8533 MT/s transfer rate exceeds Team Red's official reference figure (7500 MT/s) for the EliteBook X G1a's Ryzen AI 9 HX 375 APU. Looking further up in the Team Red "Strix Point" product stack, we spotted their Ryzen AI 9 HX PRO 375 spec sheet boasting a maximum LPDDR5x transfer speed of 8000 MT/s. Press outlets have expressed doubt when analyzing three of HP's EliteBook X G1a SKUs. Theories point to product pages containing possible placeholder information, or inaccuracies.

Working with the belief that the specs are legit, AnhPhuH commented: "this is the first laptop featured with 128 GB LPDDR5x-8533 128-bit memory. That would mean it's using four 256 Gb x32 modules(?!). As far as I know, all three major DRAM manufacturers currently only have 128 Gb x32 modules...the EliteBook X G1a uses Strix Point, not Strix Halo, so it only pairs with four x32 modules (two 64-bit channels)." HP's web shop states that the EliteBook X G1a models are due to launch on March 14. We hope that further clarification and concrete specifications appear online closer to release time. Initial pricing starts at $2749 for the lowliest of the three "128 GB LPDDR5X-8533" equipped models. The agonizingly named flagship "HP EliteBook X G1a 14 inch Notebook Next Gen AI PC Wolf Pro Security Edition" offering comes in at an eye-watering $4299.

The AOKZOE A1 X was recently teased by its maker as a new AMD Strix Point-powered gaming handheld, featuring the commendably potent Ryzen AI 9 HX 370 APU with the equally admirable RDNA 3.5-based Radeon 890M iGPU. Details were scarce regarding the handheld, but now the company has shed some much-needed light on a few features of the upcoming handheld. We still do not have a clue as to when the handheld will finally see the light of day, or even an expected price bracket. Considering that AOKZOE is not nearly as well known as its competitors in this space, the A1 X can be expected to launch with a price tag that undercuts its rivals. Thanks to a previous teaser, already know that the A1 X will sport an 8-inch 120 Hz display with VRR support.

Addressing the features teased recently, AOKZOE has revealed that the handheld will sport a 72.7 Wh battery with support for bypass charging, allowing it to draw power directly without having to pass it through the battery, thereby increasing the battery's lifespan. Moreover, the A1 X will also sport MicroSD 4.0 support, allowing for transfer speeds of up to 300 MB/s. The handheld will sport dual USB4 ports, along with an OCuLink port which will allow for speedy eGPU connections for gaming sessions that demand more horsepower than the Radeon 890M can provide. Going by the shared images, the A1 X will also sport at least one USB-A port, which will surely come in handy when the need arises for additional peripherals.

AMD today put out detailed guides on how to get DeepSeek R1 distilled reasoning models to run on Radeon RX graphics cards and Ryzen AI processors. The guide confirms that the new Ryzen AI Max "Strix Halo" processors come in hardwired to LPCAMM2 memory configurations of 32 GB, 64 GB, and 128 GB, and there won't be a 16 GB memory option for notebook manufacturers to cheap out with. The guide goes on to explain that "Strix Halo" will be able to locally accelerate DeepSeek-R1-Distill-Llama with 70 billion parameters on the 64 GB and 128 GB memory configurations of "Strix Halo" powered notebooks, while the 32 GB model should be able to run DeepSeek-R1-Distill-Qwen-32B. Ryzen AI "Strix Point" mobile processors should be capable of running DeepSeek-R1-Distill-Qwen-14B and DeepSeek-R1-Distill-Llama-14B on their RDNA 3.5 iGPUs and NPUs. Meanwhile, older generation processors based on "Phoenix Point" and "Hawk Point" chips should be capable of DeepSeek-R1-Distill-Llama-14B. The company recommends running all of the above distills in Q4 K M quantization.

Switching gears to the discrete graphics cards, and AMD is only recommending its Radeon RX 7000 series for now, since the RDNA 3 graphics architecture introduces AI accelerators. The flagship Radeon RX 7900 XTX is recommended for DeepSeek-R1-Distill-Qwen-32B distill, while all SKUs with 12 GB to 20 GB of memory—that's RX 7600 XT, RX 7700 XT, RX 7800 XT, RX 7900 GRE, and RX 7900 XT, are recommended till DeepSeek-R1-Distill-Qwen-14B. The mainstream RX 7600 with its 8 GB memory is only recommended till DeepSeek-R1-Distill-Llama-8B. You will need LM Studio 0.3.8 or later and Radeon Software Adrenalin 25.1.1 beta or later drivers. AMD put out first party LMStudio 0.3.8 tokens/second performance numbers for the RX 7900 XTX, comparing it with the NVIDIA GeForce RTX 4080 SUPER and the RTX 4090.

AMD has just published its "How to Sell" Ryzen AI MAX series guide—several news outlets have pored over the "claimed" gaming performance charts contained within this two-page document. Team Red appears to be in a boastful mood—their 1080p benchmark results reveal compelling numbers, as produced by their flagship Zen 5 "Strix Halo" processor (baseline 55 W TDP). According to Team Red's marketing guidelines, the Ryzen AI Max+ 395 APU: "competes with a GeForce RTX 4070 Mobile GPU at similar TDP and form factor." The first-party produced comparison points to their Radeon 8060S integrated graphics solution being up to 68% faster—in modern gaming environments at 1080p settings—than the competing Team Green dedicated laptop-oriented GPU, limited to 65 W TGP due to form factor restrictions. Overall, the AMD test unit does better by 23.2% on average (referring to Wccftech's calculations).

According to the document, AMD's reference system was lined up against an ASUS ROG Flow Z13 (2023) gaming laptop specced with an Intel Core i9-13900H processor, and a GeForce RTX 4070 mobile graphics card. The Ryzen AI Max+ 395's "massive iGPU" can unleash the full force of forty RDNA 3.5 compute units, paired with up to 96 GB of unified on-board memory (from a total pool of 128 GB). Non-gaming benchmarks place the flagship Team Red processor above Intel Core Ultra 9 288V and Apple M4 Pro (12-core) CPUs—as always, it is best to wait for verification from independent evaluators. Saying that, the "Strix Halo" APU family has generated a lot of excitement—even going back to early leaks—and the latest marketed performance could drum up further interest.

After several months of teasers, the Ayaneo 3 gaming handheld has finally witnessed its official launch. The product will be available with two APUs - the Ryzen 7 8840U for the entry variant, and the Ryzen AI 9 HX 370 for the high-end variant. The system can be equipped with up to 64 GB of LPDDR5X-7500 memory, and a whopping 4 TB of SSD storage. The handheld will also feature modular controllers, which can be detached with the click of a single button.

The Ayaneo 3 will also give customers the option to chose between an LCD or an OLED panel, and as VideoCardz notes, selecting the OLED option does not change the final price. As mentioned earlier, the system will be available with either a Zen 4 or a Zen 5 APU. The Strix Point variant leads the Hawk Point part by almost around 50% in multicore tests, and the HX 370's integrated Radeon 890M iGPU is somewhere around 25% more performant than the 8840U's Radeon 780M. Clearly, the performance gap between the two variants will be substantial.

As a leader in innovative technology, Acemagic is excited to announce the upcoming pre-sale launch of the F3A AI 370 MINI PC by the end of January 2025. Powered by AMD's latest Ryzen AI 9 HX 370 processor, this high-performance mini PC combines outstanding computational power with cutting-edge cooling technology, designed to meet the needs of professionals, content creators, and high-end users.

The F3A AI 370 MINI PC features an advanced 12-core, 24-thread processor, built on AMD's Zen 5 and Zen 5c architecture. With a base clock speed of 2.0 GHz and a turboboost up to 5.1 GHz, it delivers exceptional multithreaded performance and processing power. Additionally, the F3A is equipped with the third-generation Ryzen AI NPU (Neural Processing Unit) based on the XDNA2 architecture, offering up to 50 TOPS of AI computing performance. With seamless collaboration between the GPU and CPU, the F3A achieves an impressive total performance of up to 80 TOPS, making it ideal for high-demand applications like deep learning and AI inference.