It looks as though AMD might be planning to finally commercialize the more affordable version of its Ryzen AI Max APUs that have proven to be capable of powering impressively high-end gaming experiences. The first set of benchmarks of the new Strix Halo APU, dubbed the AMD Ryzen AI Max 385, have appeared on Geekbench, and the new APU is putting up some impressive numbers. AMD originally said that the Strix Halo line-up would be available between Q1 and Q2 2025, so the timing makes sense.

One major difference between the Ryzen AI Max 395 and the 385 is the iGPU, which is downgraded from the Radeon 8060S to the 8050S. When AMD launched the Strix Halo line-up, it revealed that AI Max Pro 385 would have an eight-core CPU paired with 32 graphics cores, instead of the 16-core CPU and 40-core iGPU setup. While we don't yet have GPU benchmark results for the 8050S, the CPU results put up by the APU are impressive on their own, with 2,489 points in the single-core benchmark and 14,136 points in the multicore benchmark. The laptop the new Ryzen silicon was tested in was an HP ZBook Ultra G1a with 32 GB of RAM. The results put the 385 only slightly behind the AI Max+ 395 in certain configurations, but in a similar HP ZBook Ultra G1a laptop, the Ryzen AI Max+ 395 comes out ahead of the 385 by as much as 45%. It's unclear just how much laptops with this new Ryzen AI Max Pro 385 APU will cost, but they will almost certainly be cheaper than the current crop of Ryzen AI Max+ laptops, which generally run well north of $2,000.

ZOTAC made a notable impression at Computex 2025 by unveiling a range of compact gaming and AI-ready machines combining high performance and tiny footprints. The highlight was the second-generation ZOTAC Zone handheld prototype, now powered by AMD's top-tier Ryzen AI 9 HX 370 APU. Equipped with Radeon 890M graphics, the Zone achieves smooth 1080p gameplay on its 7-inch AMOLED display, which offers a 120 Hz refresh rate and up to 800 nits of brightness. Despite its size, the device packs either 24 GB or 32 GB of LPDDR5X memory alongside a 1 TB PCIe Gen 4 SSD to ensure rapid load times and efficient multitasking.

For wireless connectivity, ZOTAC has included Wi-Fi 6E, Bluetooth 5.2, dual USB4 ports, and a microSD slot. A built-in kickstand adds flexibility to handheld play, and Hall-effect joysticks, precise triggers, and twin trackpads provide a control scheme designed for accuracy. A 48.5 Wh battery that should support extended gaming sessions is powering all this. ZOTAC also previewed its Manjaro Linux distribution on the Zone, featuring a dedicated handheld interface and Wine-based compatibility for Windows titles.

AMD announced its Radeon Open Compute (ROCm) platform with hardware acceleration support for the Ryzen AI Max 300 "Strix Halo" client processors, and the Radeon RX 9000 series gaming GPUs. For the Ryzen AI Max 300 "Strix Halo," this would unlock the compute power of the 40 RDNA 3.5 compute units, with their 80 AI accelerators, and 2,560 stream processors, besides the AI-specific ISA of the up to 16 "Zen 5" CPU cores, including their full fat 512-bit FPU for executing AVX512 instructions. For the Radeon RX 9000 series, this would mean putting those up to 64 RDNA 4 compute units with up to 128 AI accelerators and up to 4,096 stream processors to use.

AMD also announced that it has updated the ROCm product stack with support for various main distributions of Linux, including OpenSuSE (available now), Ubuntu, and Red Hat EPEL, with the latter two getting ROCm support in the second half of 2025. Lastly, ROCm gets full Windows support, including Pytorch and ONNX-EP. A preview of the Pytorch support can be expected in Q3-2025, while a preview for ONNX-EP could arrive in July 2025.

Officially, AMD Ryzen AI Max "Strix Halo" mobile processors are only available in complete systems—e.g. laptops, notebooks, and mini desktop PCs. Upon learning about this release status, DIY enthusiasts were left disappointed. After all, these impressively potent all-in-one solutions have picked up considerable praise pre- and post-launch. Team Red's "Strix Halo" flagship—the Ryzen AI Max+ 395—is the subject of much online debate, but cost of entry is steep. Under normal circumstances (i.e. no leveraging of promotional discounts), potential buyers are looking at $2000+ pre-built systems.

Separate BGA packages have turned up for sale in China—specifically on Goofish; Alibaba's second-hand trading platform. A past weekend VideoCardz investigative piece covered these curiosities. At this stage in time, viable custom motherboard designs are not yet widely distributed—effectively making individual "Strix Halo" units expensive paperweights. At the time of writing, seller "The Eraser in My Mind" offers the best Ryzen AI Max+ 395 deal: 3998 RMB (~$555 USD). This Suzhou-based trader also lists Ryzen AI Max PRO 390, and 380 SKUs. Product descriptions indicate that some of these processors are already powering mysterious handheld gaming devices (likely regional exclusives). Four Goofish accounts are displaying the same set of images; distinctive Team Red branding and "Made in Taiwan" tags are clearly visible across specimens—mostly mounted on plastic transport trays.

Zotac is ready with the Magnus EA (2025) mini PC powered by AMD Ryzen AI Max "Strix Halo" line of processors. It was inevitable for "Strix Halo" to make its way into gaming-capable mini PCs, given its small PCB and cooling footprint for the kind of hardware chops on offer—up to 16 "Zen 5" CPU cores, and a powerful iGPU with up to 40 RDNA 3.5 compute units that makes it capable of 1440p AAA gaming; besides full Microsoft Copilot+ capability with a 50 TOPS-class NPU. The Magnus EA comes in a similar 140 mm-class 1U chassis as the 2025 Magnus One that's expected to be built on Core Ultra 200V "Lunar Lake" processors, which is noticeably thinner than the 2025 Magnus EN, which combines a Core Ultra 200H "Arrow Lake-H" processor with GeForce RTX 50-series "Blackwell" mobile discrete GPUs. Zotac is expected to unveil the Magnus EA, the 2025 Magnus EN, and the 2025 Magnus One at Computex, later this month.

Around the middle of March, GMKtec's EVO-X2 Mini PC design attracted international media attention—thanks to Dr. Lisa Su's autograph adorning a special presentation sample. During festivities, this relatively young Chinese brand—founded back in 2019—introduced the "world's first" AI mini PC equipped with AMD's Ryzen AI Max+ 395 APU. This flagship "Strix Halo" chip leverages Zen 5 and RDNA 3.5 technologies; the latter aspect forms the basis of an impressively potent Radeon 8060S iGPU. This integrated graphics solution has surpassed or matched some worthy (previous-gen) discrete competitors, and apparently performs admirably in LLM inference workload scenarios. At the tail end of March, GMKtec opened up pre-orders for its $2000+ headline product—starting off in China. Back then, potential international buyers were intrigued—many envisioned a pleasing wider distribution of EVO-X2 Mini PC retail stock. Given that GMKtec had semi-recently expanded its sales operation into Europe, hopes were elevated.

As reported by TechRadar last week, Eurozone tech enthusiast prayers were answered—their coverage outlined an intriguing pre-order campaign: "buyers can unlock a reduced pre-sale price of €1,499 for the base model by paying a $100 deposit. Those who want the higher configuration need to place a €200 deposit to qualify for a discounted €1,799 final price. All orders must be completed by May 7 to receive the full discount." Days later, VideoCardz and Notebookcheck noted a similar promotion—rolled out for North American audiences. Officially, the EVO-X2 Mini PC is (tentatively) set to launch on May 20—well ahead of Framework's projected "early Q3 2025" debut shipment of "tiny 4.5L Mini-ITX" Desktop units. Time limited promo prices are in effect until next week—the 64 GB and 128 GB RAM EVO-X2 package are currently discounted: $1399 and $1799 (respectively). As expected, GMKtec's official US webshop also requires pre-order deposits—refer to these details below.

Today, Chinese PC maker FEVM introduced the FA‑EX9 mini PC, powered by AMD's new Ryzen AI MAX+ 395 "Strix Halo" processor. This compact system measures just 192 × 190 × 55 mm (2 L volume) and packs 16 Zen 5 CPU cores alongside 40 RDNA 3.5 compute units (Radeon 8060S) and a dedicated XDNA 2 neural engine capable of 50 TOPS. FEVM configures the MAX+ 395 to run at up to 120 W sustained power, putting it in the same performance class as a Ryzen 9 9955HX paired with an RTX 4070 Laptop GPU. Memory comes as 128 GB of LPDDR5X on a 256‑bit bus, with up to 96 GB usable as video memory for large‑model inference. Storage is handled by dual M.2 PCIe 4.0 SSD slots, supporting up to 2 TB onboard and up to 16 TB total. The FA‑EX9 offers one HDMI 2.1 port, one DisplayPort 1.4, two USB4 Type‑C connectors for up to four 8K displays, and an OCuLink port for external GPU expansion. Inspiration for this mini PC seems to be NVIDIA's DGX Spark, which is Team Green's custom solution for local AI processing in an incredibly compact housing.

In comparison, NVIDIA's DGX Spark brings the GB10 Grace Blackwell superchip to a palm‑sized AI appliance. It combines a 20‑core Arm CPU cluster with a Blackwell GPU featuring next‑gen Tensor and RT cores, delivering up to 1,000 FP4 AI TOPS. The DGX Spark is built around 128 GB of unified LPDDR5X memory at 273 GB/s, up to 4 TB of self‑encrypting NVMe storage, four USB4 ports, one HDMI output, and a ConnectX‑7 SmartNIC providing 200 GbE networking for multi‑node clusters. Its chassis measures 150 × 150 × 50.5 mm (1.24 L volume) and draws approximately 170 W under load, with pricing starting at $2,999 for a 1 TB model or $3,999 for the 4 TB Founder's Edition, now available for preorder. While the FA‑EX9 balances general‑purpose computing, flexible GPU expansion, and high‑speed I/O for edge AI and creative professionals, the DGX Spark focuses on out‑of‑the‑box AI throughput and scale‑out clustering. The FA-EX9 is more of a general-purpose Swiss army knife, which can be used for anything from AI to gaming. Release date and pricing are still unknown.

TechPowerUp today released the latest version of TechPowerUp GPU-Z, the popular graphics sub-system information, monitoring, and diagnostic utility. Version 2.65.1, launched in conjunction with v2.65.0, comes with support for desktop GeForce RTX 5060 Ti 16 GB, RTX 5090 Laptop, RTX 5080 Laptop, RTX 5070 Ti Laptop, RTX Pro 4000 Blackwell, RTX Pro 3000 Blackwell, and NVIDIA H200. Support is also added for the upcoming AMD Radeon RX 9070 GRE, and the iGPU of Ryzen AI 300 "Krackan Point" and "Strix Halo." Other new GPUs support was added for is the Intel Arc A750E and A580E. Lastly, we are introducing support for Moore Threads S3000 MTvGPU-1108. A bug that caused GPU Compute checkboxes to go missing in the non-English localization of GPU-Z (which emerged with 2.65.0), has been fixed.

DOWNLOAD: TechPowerUp GPU-Z 2.65.1

Over the past weekend, GMKtec's Weibo channel announced that pre-orders for its recently unveiled EVO-X2 mini PC model will start on April 7 (through JD.com), for customers located in China. Almost two weeks ago, the manufacturer boasted about its brand-new offering being the "world's first AI mini PC" equipped with AMD's Ryzen AI "Strix Halo" Max+ 395 APU. Extra international attention was gained, due to Lisa Su's autographing of a showcased unit during proceedings at the 2025 AI PC Innovation Summit (held on March 18, in Beijing). Pricing and availability were not mentioned during this press event, but GMKtec's Saturday (March 29) bulletin has revealed a (roughly) $2067 USD price point for the EVO-X2 launch model.

The manufacturer's blog entry stated that the: "EVO-X2 AI supercomputing host is coming, 128 GB + 2 TB priced at 14999 yuan, pricing reconstructs the desktop computing power boundary! Equipped with AMD Ryzen AI Max+ 395 flagship processor, 16-core 32-thread architecture with 5.1 GHz acceleration frequency, combined with 128 GB LPDDR5X memory and 2 TB high-speed storage, it can realize local deployment of 70 billion parameter large models, and AI performance exceeds NVIDIA's GeForce RTX 5090D graphics card." This potent compact AI-crunching solution is tempered by GMKtec's "innovative" Arctic Ocean cooling system. They advertise this design as using: "dual-turbofans and VC heat sinks to achieve silent heat dissipation at a peak power consumption of 140 W. The body adopts a recycled aluminium suspension design, equipped with HDMI, DP and USB4 interfaces, and supports Wi-Fi 6 + 2.5G network access." The brand has not yet announced an international release, but their EVO-X2 mini PC could face serious competition. Late last month, Framework debuted its Desktop product range—consisting of configurable 4.5L Mini-ITX systems—with a top-end Ryzen AI Max+ 395 (128 GB) model starting at $1999.

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.

Well, the wait is over and early reviews for AMD's Strix Halo APUs have finally dropped. For those who kept up with the leaks and rumors, the high-end RDNA 3.5 Radeon 8060S iGPU was repeatedly rumored to features up to 40 CUs, allowing for raw performance that keeps up with several discrete-class mobile GPUs. Now that we have concrete information, it appears that the Strix Halo iGPU does indeed trade blows with mid-range mobile GPUs, which is an undeniably impressive feat for an integrated unit. Some of the fastest x86 iGPUs - the Arc 140 V, Radeon 890M, are all left in the dust, although Apple's highest-end offerings are unsurprisingly well ahead.

Starting off with 3D Mark Time Spy, the 40-CU Radeon 8060S, housed in the 13-inch ROG Flow Z13, managed an impressive score of 10,200 points according to Notebookcheck. This puts the iGPU in close proximity to other RTX 4070-powered 14-inch gaming laptops, such as the Zephyrus G14 which managed to rake in around 10,300 points. Compared to the previous iteration of the ROG Flow Z13, which boasts a 65-watt RTX 4070, the Radeon 8060S-powered Z13 pulls ahead by around 5%. Laptops with more substantial power envelopes do race ahead significantly, such as the 140-watt RTX 4070 Laptop-powered Razer Blade 14 which managed over 13,000 points. In the Steel Nomad benchmark, however, the Radeon 8060S appears less impressive, trailing behind not only the RTX 4070 Laptop, but also systems with the RTX 4060 Laptop GPU (110 W).

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.

Late last month, an AMD "How to Sell" Ryzen AI MAX series guide appeared online—contents provided an early preview of the Radeon 8060S iGPU's prowess in 1080p gaming environments. Team Red seemed to have some swagger in their step; they claimed that their forthcoming "RDNA 3.5" integrated graphics solution was up to 68% faster than NVIDIA's discrete GeForce RTX 4070 Mobile GPU (subjected to thermal limits). Naturally, first-party/internal documentation should be treated with a degree of skepticism—the PC hardware community often relies on (truly) independent sources to form opinions. A Chinese leaker has procured a pre-release laptop that features a "Zen 5" AMD Ryzen AI Max+ 395 processor. By Wednesday evening, the tester presented benchmark results on the Tieba Baidu forums.

The leaker uploaded a screenshot from a 3DMark Time Spy session. No further insights were shared via written text. On-screen diagnostics pointed to a "Radeon 8050S" GPU, and the CPU being an "AMD Eng Sample: 100-000001243-50_Y." Wccftech double-checked this information; they believe that the OPN ID corresponds to a: "Ryzen AI MAX+ 395 with the Radeon 8060S, instead of the AMD Radeon 8050S iGPU...The difference between the two is that the Radeon 8060S packs the full 40 Compute Units while the Radeon 8050S is configured with 32 Compute Units. The CPU for each iGPU is also different and the one tested here packs 16 Zen 5 cores instead of the 12 Zen 5 cores featured on the Ryzen AI MAX 390." According to the NDA-busting screenshot, Team Red's Ryzen AI MAX+ 395 engineering sample racked up an overall score of 9006 in 3DMark Time Spy. Its graphics score tally came in at 10,106, while its CPU scored 5571 points. The alleged Radeon 8060S iGPU managed to pull in just under NVIDIA's GeForce RTX 4060 Mobile dGPU (average) score of 10,614. The plucky RDNA 3.5 40 CU iGPU seems to outperform a somewhat related sibling; the Radeon RX 7600M XT dGPU (with 32 RDNA 3 CUs) scored 8742 points. Radeon 8060S trails the desktop Radeon RX 7600 GPU by 884 points.

Apple's M4 SoC was released to overwhelmingly positive reviews, particularly regarding the commendable performance and efficiency benefits it brought to the table. The chip first appeared in the OLED iPad Pro lineup last May, arriving in the company's MacBook Pro lineup only much later, giving Intel's Lunar Lake and AMD's Strix Point a run for their money. Now, it appears that the company is cognizant of the heat brought by AMD's Strix Halo, and has already commenced mass production for the first SoC in the M5 family - the vanilla M5, according to Korean news outlet ET News.

Just like last time, the M5 SoC has been repeatedly rumored to first arrive in the next-generation iPad Pro, scheduled to enter production sometime in the second half of this year. The MacBook Pro will likely be next-in-line for the M5 treatment, followed the rest of the lineup as per tradition. Interestingly, although Apple decided against using TSMC's 2 nm process for this year's chips, the higher-tier variants, including the M5 Pro and M5 Max are expected to utilize TSMC's SoIC-mH technology, allowing for vertical stacking of chips that should ideally benefit thermals, and possibly even allow for better and larger GPUs thanks to the separation of the CPU and GPU portions. Consequently, yields will also improve, which will allow Apple to bring costs down.

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.

ASUS is working on a new line of NUC mini PCs powered by the AMD Ryzen AI MAX "Strix Halo" mobile processors that come with oversized iGPUs and CPU core counts as high as 16-core/32-thread "Zen 5." This was sniffed out in shipping manifests by Olrak29_ on its way to being tested by the BIS (Bureau of Indian Standards) for regulatory certification similar to CE, with the manifest describing the NUC model as the "NUC14LNS," meaning that this box is from the NUC 14 series. The manifest describes the NUC sample as featuring the top of the line Ryzen AI MAX+ 395.

The Ryzen AI MAX+ 395 maxes out everything on the silicon, featuring 16 "Zen 5" CPU cores across two CCDs with full 512-bit FPUs, with 80 MB of "total cache" (L3+L2) between them; a 50 TOPS-class NPU that can locally accelerate Microsoft Copilot+, and that large RDNA 3.5 iGPU with 40 compute units (2,560 stream processors), 80 AI accelerators, and 40 ray accelerators. What's interesting about this NUC is that it will not come with SO-DIMM slots, since the "Strix Halo" SoC features a 256-bit wide LPDDR5X memory interface. It will either have hardwired memory, or use a pair of LPCAMM2 modules (each with a 128-bit bus width), which is less likely. With all the rage about AI developers using M4-powered Mac minis to accelerate DeepSeek, is ASUS eying a slice of the AI market?

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.

Thanks to the informative breakdown by Chips and Cheese, we are learning that AMD's latest Ryzen AI processors for laptops, codenamed "Strix Halo," utilize a parallel "sea of wires" interconnect system between their chiplets, replacing the SERDES (serializer/deserializer) approach found in desktop Ryzen models. The processor's physical implementation consists of two Core Complex Dies (CCDs), each manufactured on TSMC's N4 (4 nm) process and containing up to eight Zen 5 cores with full 512-bit floating point units. Notably, the I/O die (IOD) is also produced using the N4 process, marking an advancement from the N6 (6 nm) process used in standard Ryzen IODs on desktops. The key change lies in the inter-chiplet communication system. While the Ryzen 9000 series (Granite Ridge) employs SERDES to convert parallel data to serial for transmission between chiplets, Strix Halo implements direct parallel data transmission through multiple physical connections.

This design achieves 32 bytes per clock cycle throughput and eliminates the latency overhead associated with serialization/deserialization processes. The parallel interconnect architecture also removes the need for connection retraining during power state transitions, a limitation present in SERDES implementations. However, this design choice necessitates additional substrate complexity due to increased connection density and requires more pins for external connections, suggesting possible modifications to the CCD design compared to desktop variants. AMD's implementation required more complex substrate manufacturing processes to accommodate the dense parallel connections between chiplets. The decision to prioritize this more challenging design approach was driven by requirements for lower latency and power consumption in data-intensive workloads, where consistent high-bandwidth communication between chiplets is crucial.

At CES, AMD unleashed the much awaited Ryzen AI Max "Strix Halo" APUs with mammoth iGPUs, up to a whopping 40 CUs for the Radeon 8060S. These chips are powerful enough to not require discrete graphics at all, making them ideal for mini PCs, which lack the physical room for dedicated graphics. GMK appears to be among the first to announce a mini PC with the top-end Ryzen AI Max+ 395 APU, although any further details are under wraps as of now.

Unlike the Strix Point parts, Strix Halo abandons the smaller and more efficient Zen 5c cores for a Zen 5-only setup, with up to 16 Zen 5 cores for the highest-end Ryzen AI Max+ 395 SKU. This allows for some serious performance potential, with AMD promising substantially better performance than both Intel's Lunar Lake and Apple's M4 Pro, although it would be much fairer to compare Strix Halo to Apple's M4 Max, and Intel's Arrow Lake-H/X instead. Regardless, there is no denying Strix Halo APUs open up new doors in terms of performance for compact systems, the rest remains to be seen as and when the products reach reviewers.

ASUS Republic of Gamers (ROG) today announced the arrival of the 2025 ROG Flow Z13, a powerful gaming tablet. This versatile 2-in-1 gaming machine now features the brand new ultra-powerful AMD Ryzen AI Max+ 395 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.

AMD at the 2025 International CES debuted the Ryzen AI Max 300 series of mobile processors. These chips are designed to go up against the Apple M4 Pro, or the chip that powers the Apple MacBook Pro. The idea behind it is to provide leadership CPU and graphics performance from a single package, minimizing the PCB footprint from having a discrete GPU. In stark contrast, the Intel Core Ultra 200V "Lunar Lake," is designed more to go against the Apple M4, or the chips that power the latest MacBook Air but not quite the MacBook Pro. What sets "Strix Halo" functionally apart from "Lunar Lake" or even the M4 Pro, is that the AMD chip doesn't have memory-on-package (MoP), it relies on discrete LPDDR5X memory chips.

The "Strix Halo" processor is "Fire Range" on steroids. There are one or two "Zen 5" CCDs, for up to a 16-core/32-thread core configuration. Each of these "Zen 5" cores are unlike the ones on "Strix Point," in that they feature a fully unlocked AVX512 hardware pipeline (512-bit FP). The CCD shares a lavish 32 MB of L3 cache among 8 "Zen 5" cores. This is hardly the star attraction. Unlike "Fire Range," which features the small 6 nm client I/O die from "Granite Ridge," The new "Strix Halo" features a massive SoC die built on the 5 nm EUV foundry node. This packs the star attraction of the processor, it's oversized iGPU that has a massive 40 compute units (2,560 stream processors).

AMD is at the 2025 International CES, and we join them for a brisk run of what they have in store for us through the year. We expect some important announcements, such as the next-gen Radeon RX gaming GPUs powered by RDNA 4, a new flagship desktop processor powered by 3D V-Cache technology, HX-segment Ryzen 9000 series processors for gaming notebooks and portable workstations, the fabled "Strix Halo" chip AMD plans to surprise Apple with; and a fleshing out of its mobile processor portfolio.19:02 UTC: The show is underway.19:02 UTC: Jack Huynh takes centerstage.

AMD fans are undoubtedly on their toes to witness the performance improvements that Strix Halo is ready to bring forth. Unlike Strix Point, which utilizes a combination of Zen 5c and full-fat Zen 5 cores, Strix Halo will do away with the small cores for a Zen 5 "only" setup, allowing for substantially better multicore performance. Moreover, it is also widely expected that Strix Halo will boast chunky iGPUs that will bring the heat to entry-level and even some mid-range mobile GPUs, allowing Strix Halo systems to not require discrete graphics at all, with a prime example being the upcoming ROG Flow Z13 tablet.

As per recent reports, the upcoming Ryzen AI Max+ Pro 395 APU will sport an RDNA 3.5-based iGPU with a whopping 40 CUs, and will likely be branded as the Radeon 8060S. In a leaked Geekbench Vulkan benchmark, the Radeon 8060S managed to outpace the RTX 4060 Laptop dGPU in performance. However, according to yet another leaked benchmark, Passmark, the Radeon 8060S and the 32-CU 8050S scored 16,454 and 16,663 respectively - and no, that is not a typo. The 8060S with 40 CUs is marginally slower than the 8050S with 32 CUs, clearly indicating that the numbers are far from final. That said, performance in this range puts the Strix Halo APUs well below the RTX 4070 laptop GPU, and roughly the same as the RTX 3080 Laptop. Not bad for an iGPU, although it is almost certain that actual performance of the retail units will be higher, judging by the abnormally small delta between the 8050S and the 8060S.

AMD's interim RDNA 3.5 architecture will power the Radeon RX 8000 series integrated graphics in "Strix Halo" mobile processors, while the more advanced RDNA 4 architecture is reserved for the higher-tier Radeon RX 9000 series of discrete graphics, according to @9550pro on X. We previously believed that AMD's Ryzen AI MAX 300 Strix Halo processors would carry an iGPU with Radeon 8000S branding. However, at the same time, we expected the Radeon RX 8000 series of desktop GPUs to have a similar branding while being powered by RDNA 4. The new Radeon naming scheme is now transparent, thanks to the latest leaks of the naming schemes and early glimpses of reference design.

The RDNA 4-based RX 9000 series will be powered by the Radeon RX 9070 XT, built on the Navi 48 silicon. This GPU represents AMD's new focus on the high-volume midrange performance segment rather than competing in the ultra-enthusiast high-end space. The architecture promises enhanced SIMD IPC performance and a specialized ray tracing solution that significantly reduces performance overhead compared to current offerings. According to All The Watts, the RX 9000 lineup is expected to include various SKUs across different performance tiers, including the RX 9060, 9050, and 9040 series. Meanwhile, the RDNA 3.5-powered RX 8000 series will serve as a refined iteration of the current RDNA 3 generation. Still, they will be exclusive to AMD's mobile segment in the form of iGPU, integrated inside Strix Halo APU. Both RDNA 4 GPUs and RDNA 3.5-based APUs are scheduled for the CES 2025 event unveiling in January.

Last week, we reported on a massive leak that gave us a glimpse at a surfeit of upcoming ROG gaming laptops from ASUS boasting Arrow Lake-HX and Strix Halo processors, along with RTX 50-series Laptop GPUs. The company has now gone ahead and officially teased its ROG Flow Z13 laptop and the ROG Strix 18 laptop, the videos for which were obtained by VideoCardz. Considering that these were just teasers, the details shared were sparse, but undoubtedly intriguing regardless.

The ROG Strix 18, will likely boast the Core Ultra 9 285HX and Core Ultra 9 275HX CPUs along with NVIDIA "Blackwell" Laptop GPUs, with up to an 175-watt RTX 5090 Laptop with 16 GB of GDDR7 VRAM. Multiple other GPU options will also be available, with the RTX 5070 Ti Laptop GPU being the entry-point as per the leaked listings. Clearly, the Strix 18 is poised to be a powerful and power-hungry desktop replacement-class laptop, along with a massive 18-inch mini LED screen with a speedy 240 Hz refresh rate. Needless to say, the G18 has no intention of being affordable.