Apple today debuted M6 in the new Mac mini and M5 Ultra in the new Mac Studio, providing an extraordinary leap in performance and AI capabilities. M6, Apple's first state-of-the-art 2-nanometer chip, advances every compute block, delivering gains across every dimension of performance. The chip features a larger 12-core CPU complex with the world's fastest CPU core, a larger 12-core GPU with Neural Accelerators, a Dual 16-core Neural Engine, and up to 170 GB/s of unified memory bandwidth.

M5 Ultra, the ultimate powerhouse for pro and AI workloads, uses next-generation UltraFusion technology to form a quad-die architecture for the first time in an M-series system on a chip (SoC). The chip includes an up-to-36-core CPU and up-to-80-core GPU with a massive 1.2 TB/s of unified memory bandwidth, 50 percent more than M3 Ultra. With their advanced technologies, these SoCs deliver extraordinary compute with industry-leading power efficiency, empowering users to do even more on a desktop.

Recently, new Intel Nova Lake-S iGPU IDs were added to the Linux kernel driver stack, revealing that Intel may be planning to launch as many as seven SKUs in the Core Ultra 400 desktop CPU series. Until a new rumor by leaker @jaykihn0 on X, however, little was known about the upcoming Nova Lake-H and Nova Lake-S CPUs and their iGPU configurations. The leaker claims that Intel's Nova Lake-S desktop line-up will feature at least one SKU with a 12-core Xe3P iGPU configuration.

A 12-core Xe3P iGPU solution would conceivably be a worthwhile entry-level dGPU replacement, given the performance observed in tests of the current Xe3 B390 iGPU. The leaker also tips that Nova Lake-H, the upcoming mobile CPU line-up, will feature several 12-core Xe3P configurations, similar to the current Core Ultra X7 358H and Core Ultra X9 388H SKUs which both feature 12 Xe3 cores, while lower-end Nova Lake-S and -H parts will fall back to 4 Xe3 or 2 Xe3 configurations. There is no word on whether there will be a 10-core Xe3 or Xe3P iGPU SKU as there is with the Arc G3 handheld gaming CPU family. These leaks come not too long after another rumor revealed that Intel's Xe3P iGPU architecture is expected to be significantly faster than even the current Arc B390 iGPU that has taken the crown for high-performance integrated graphics from the likes of AMD's Radeon 890M.

Intel Core 200 "Bartlett Lake" is probably the most interesting processor gamers can't buy—built on the Intel 7 node and designed for Socket LGA1700, "Bartlett Lake" is a non-Hybrid, pure P-core chip, a monolithic silicon, with 12 "Raptor Cove" P-cores, and no E-core clusters. The 12-core/24-thread chip was launched earlier this month as an exclusive for the commercial and industrial PC OEM markets, as an edge AI PC processor, it is not drop-in compatible with consumer Intel Z790 chipset motherboards, or at least that was the plan.

A motherboard UEFI firmware mod by "kryptonfly" got a consumer ASUS Z790-AYW OC motherboard to POST with an Intel Core 9 273QPE "Bartlett Lake" processor. The modder used Claude AI to mod the UEFI firmware of the board without tripping safeguards that prevent the motherboard from booting with modded firmware. The 273QPE is a 12-core/24-thread pure P-core processor with 2 MB of L2 cache per core, and 36 MB of shared L3 cache. Its uncore components and iGPU are carried over from "Raptor Lake-S." The 273QPE has a base frequency of 3.30 GHz, an all-core boost frequency of 5.30 GHz, and a single-core TVB frequency of 5.90 GHz. The chip has 125 W processor base power, and 250 W maximum turbo power. You can watch kryptonfly's firmware mod video from the source link below.

Factory automation, physical AI in mobile robotics, and other AI-driven edge applications are rapidly evolving and driving the need for computing platforms that provide real-time AI processing, deterministic performance, and long-term reliability in always-on environments.

To meet these needs, AMD is expanding its AMD Ryzen AI Embedded P100 Series processor portfolio. New processors feature up to 2x higher CPU core counts, up to 8x higher graphics processing unit (GPU) compute, and an estimated 36% higher system tera operations.

AMD announced its Ryzen AI 400 series "Gorgon Point" mobile APUs based on Zen 5 and Zen 5c cores at CES 2026 earlier this year, simultaneously showing off the AM5-based Ryzen AI 400-branded desktop APUs at the same show. Now, according to a new leak by Moore's Law is Dead on X, AMD will allegedly launch the new Ryzen AI 400-series desktop processors for AM5 in the first half of 2026. MLID adds that the launch may even happen as early as Q1. He also released what he claims to be a short promotional video of an AMD Ryzen AI 400 Pro processor in an AM5 socket to lend credence to his leak.

Exact specifications for the AM5 APUs are unconfirmed, but if they're anything like the laptop counterparts, it is expected that the new APUs will launch with the same silicon as Strix Point but with adjusted power management and increased clock speeds. This means we can expect to see the Ryzen AI 400 desktop processors top out with a 12-core (4× Zen 5; 8 × Zen 5c) CPU cluster tied to a 16 CU RDNA 3.5 iGPU, and a 60 TOPS NPU.

Ayaneo launched the Pocket Fit in mid-2025 as a Snapdragon-powered Android gaming handheld, and it has now brought that compact form factor and minimalist design over to the Windows gaming handheld world with the Ayaneo Konkr Fit. The new Konkr Fit bumps up the screen size from the 6-incher on the Pocket Fit to a 7-inch, 1080p, 16:9 OLED display, and moves away from the Arm architecture entirely, opting instead for the AMD Ryzen AI 9 HX 470, which is a 12-core Zen 5 CPU with the 16-CU Radeon 890M iGPU. Ayaneo has also confirmed that the display will be capable of 800 nits of brightness. It has not yet been confirmed, but the Konkr Fit is likely to use the same Hall effect joysticks and triggers as the Pocket Fit. It will seemingly have dual USB-C ports along the top edge. In terms of physical dimensions, it looks almost identical to the ASUS ROG Ally, if not somewhat smaller in terms of the top-to-bottom measurement.

In the announcement video, Ayaneo shows off the TDP configuration overlay, and it seems as though the APU will be able to reach 40 W or go down to as low as 3 W. How it manages to stay cool at those high TDPs is yet to be seen, but Ayaneo did show the gaming handheld running Black Myth: Wukong on the video as well. The battery is slated to be an 80 Wh unit, which should be plenty for the small OLED screen and with the APU restricted to lower power consumption. The diminutive handheld will compete directly with the likes of the ASUS ROG Ally X and the Lenovo Legion Go 2, both of which feature similarly powerful AMD APUs and run on Windows. Pricing and availability have yet to be confirmed, although it's unlikely to be cheap, given the current trends in PC hardware and pricing.

Late last week, a not-yet-released Intel "Core 7 253PE" processor model leaked out via the PassMark CPU benchmark database. This ten P-Core (all performance) candidate signalled the first signs of "Bartlett Lake-S" activity in 2026, after many months of silence. Over the past weekend, additional "Team Blue Refreshed" product discoveries have been made. On Saturday (January 17) Vectral555 highlighted three new SKUs, but did not reveal the actual source of these leaks. Screenshots show model names, codes, and very basic specifications—evidently, these grabs were lifted from premature listings published by Mouser Electronics UK. The three unreleased OEM/tray products are categorized as Core 9 SKUs, all featuring 36 MB of cache, and destined for deployment on Team Blue's "FC-LGA16A" platform—this unusual socket name seems to be another way to refer back to the familiar LGA 1700 insert.

The "273PQE" model is boost clocked the highest at a maximum 5.9 GHz, the "273PE" SKU is specced at a max. 5.7 GHz, and the "273PTE" option makes do with 5.5 GHz. At the time of writing, the British wholesaler is offering both single unit and bulk orders. The fanciest "Core 9 273PQE" model is "on order" with zero units in stock, but tagged with £657.04 (single order) and £579.17 (bulk order, ten or more units) prices. The other options—"273PTE" and "273PE"—seem to be "non-stocked," and cost the same: £629.00 (single) or £554.46 (bulk). Intel could be prepping "Bartlett Lake-S" processors—under "Core Series 2" naming convention—for imminent launch. Two days ago, ITHome shared an impressively comprehensive list of Core 5, 7, and 9 model names plus basic spec credentials.

The first benchmark results of AMD Ryzen AI MAX+ 392, part of the Strix Halo family announced last week at CES 2026, have surfaced and are looking good. Quick recap on this particular SoC from AMD designed for more accessible gaming laptops. The Ryzen AI Max+ 392 is a 12-core/24-thread CPU using two CCDs, clock speeds of 3.2 GHz base and boost clocks reaching 5.0 GHz, a full-featured Radeon 8060S iGPU with all 40 CU enabled, a 50 TOPS NPU, and a configurable TDP range of 45 W to 120 W. The platform supports LPDDR5X memory speeds up to 8533 MT/s and configurations with up to 128 GB of memory.

Performance data comes from an ASUS TUF Gaming A14 (TX Air FA401EA) laptop running the Ryzen AI MAX+ 392 with 64 GB of LPDDR5X memory at 8000 MT/s. In Geekbench 6, the system achieved scores of 2,917 points (single-core) and 18,071 points (multicore). That multicore result slightly edges out the desktop Ryzen 9 7900X and comes close to newer Zen 5 desktop parts. These early results suggest that more affordable AMD Strix Halo SKUs still deliver strong CPU throughput while maintaining a high-end iGPU configuration. Laptops based on Ryzen AI MAX+ 392 and Ryzen AI Max+ 388 (8-core/16-thread CPU, single CCD, 3.60 GHz base with 5.00 GHz boost) are expected to arrive in retail during the first half of the year.

Tiiny AI Inc. (www.tiiny.ai), a US deep-tech AI startup, today unveiled the world's smallest personal AI supercomputer, the Tiiny AI Pocket Lab, officially verified by Guinness World Records under the category "The Smallest MiniPC (100B LLM Locally)." The event marked the first global public unveiling of the Tiiny AI Pocket Lab. For the first time in AI supercomputing, a pocket-sized device is capable of running up-to a full 120-billion-parameter large language model (LLM) entirely on-device—without cloud connectivity, servers, or high-end GPUs.

Designed for energy-efficient personal intelligence, Tiiny AI Pocket Lab runs within a 65 W power envelope. It can enable large-model performance at a fraction of the energy and carbon footprint of traditional GPU-based systems.

Minisforum announces the global launch of the MS-R1, the world's first Arm-based Mini workstation supporting UEFI boot and multi-system virtualization. Compact, efficient, and highly expandable, the MS-R1 redefines what desktop Arm computing can achieve - marking a major step towards bringing server-grade Arm performance to the desktop.

Plug-and-Play Arm Performance for Endless Possibilities
Minisforum introduces the MS-R1, powered by the CIX CP8180, an innovative Arm processor designed to push Arm performance to new heights. Powered by the CIX CP8180 processor with 12 cores and 12 threads, the MS-R1 combines exceptional computing efficiency (28 W TDP) with 45 TOPS of AI performance, including 28.8 TOPS of NPU acceleration for faster, more responsive AI inference and edge workloads. Users can expect smoother multitasking, quicker model training, and more energy-efficient computing-bringing Arm-based performance once reserved for data centers directly to the desktop.

A month ago, AMD launched the Ryzen Threadripper PRO 9000 WX-Series of processors, but at the time, the company didn't provide any pricing. Today, in a blog post, the company revealed the pricing for five of the six new Threadripper processors, skipping the 12-core 9945WX for some reason. As these are workstation chips with up to 96 cores, pricing is accordingly high, with the 16-core 9955WX coming in at US$1,649. The 24-core 9965WX comes in at US$2,899, followed by the 32-core 9975WX at US$4,099. Things start to get really eye watering with the 64-core 9985WX at US$7,999 and finally the 96-core 9995WX at US$11,699.

In all fairness, the per core cost actually gets a lot lower with the two high-end parts, but it's pretty clear that these 350 W TDP chips are not intended for consumer use. AMD also added some new benchmark figures, comparing the 9995WX with Intel's Xeon W9-3595X. AMD claims to best it by between 40 and 145 percent, depending on the benchmark in question. It's a bit of an unfair comparison though, as the W9-3595X is only a 60-core CPU that has an MSRP of US$5,889, but Intel doesn't have any higher-end options in its workstation lineup either. It would've made more sense to put the W9-3595X up against the 9985WX though, as the two are closer both in terms of core count and price point.

Chinese tech news sites have alluded to the launch of Colorful's brand-new SMART 900 Mini PC in the region. Oddly, the company's various web presences and social media accounts do not mention this diminutive 4-liter (volume) product. At last month's Computex trade show, the TechPowerUp crew happened upon a preview unit—dubbed generically as a "Mini AI PC." The latest press material confirms Colorful's selection of AMD's top-flight 16-core Ryzen AI Max+ 395 APU. The Team Red "Strix Halo" mobile series leverages "Zen 5" processor cores and RDNA 3.5 integrated graphics solutions. Colorful has joined a small club of Mini PC providers that deal in Ryzen AI Max-equipped hardware. GMKtec seems to be leading this pack; with last month's global release of configurable EVO-X2 Mini PC pre-builds (starting at $1499).

Zotac is readying a competing Magnus EA (2025) range; the TPU team encountered a 12-core Ryzen AI Max 390-equipped example at Computex 2025. In North America, Framework is still working on getting its "4.5L Mini-ITX" Desktop out of the door—hopefully by the third quarter of this year. Colorful's SMART 900 Mini PC design sports a high quality anodized aluminium chassis. An "excellent" heat dissipation solution is advertised as taking: "advantage of the metal body—ensuring that the system can maintain a low operating temperature and a relatively reasonable noise level under high load." Rival manufacturers have outlined memory configurations of 64 GB or 128 GB LPDDR5X, but Colorful has opted for an unusual in-between 96 GB setup. At the time of writing, no SMART 900 Mini PC pricing information was included in local media reports.

Today, MediaTek unveiled its latest chipset in the flagship space, the MediaTek Dimensity 9400e. Featuring the company's advanced All Big Core architecture, the Dimensity 9400e is the latest addition to MediaTek's family of flagship-class processors, providing a wider variety of options and functionality for device makers, and delivering exceptional performance and energy efficiency for outstanding artificial intelligence, connectivity, imaging, and gaming for users.

"With the launch of the MediaTek Dimensity 9400e, we are expanding our family of leading mobile platforms to ensure both device makers and users can select from a larger range of flagship experiences than ever before," said Dr. Yenchi Lee, General Manager of MediaTek's Wireless Communications Business Unit. "We remain committed to exceeding expectations in top-tier performance, energy efficiency, and AI capabilities by combining powerful hardware with advanced MediaTek-driven technologies."

MediaTek today announced the Dimensity 9400+ SoC, the latest addition to MediaTek's Dimensity flagship chipset family. Providing exceptional Generative and agentic AI capabilities as well as other performance enhancements, the Dimensity 9400+ supports the latest Large Language Models (LLM) while sustaining a super power-efficient design. The Dimensity 9400+ features an All Big Core design, integrating one Arm Cortex-X925 core operating up to 3.73 GHz, combined with 3x Cortex-X4 and 4x Cortex-A720 cores. This powerful configuration accelerates single and multithreaded performance for top-tier Android UX experiences.

"The MediaTek Dimensity 9400+ will make it easier to deliver innovative, personalized AI experiences on-device, combined with enhanced overall performance to ensure your device can handle all tasks with ease," said JC Hsu, Corporate Senior Vice President at MediaTek. "We are working closely with developers and manufacturers to continue building a robust ecosystem of AI applications and other features that will bring a number of speed and privacy benefits to consumers."

AMD's next-generation Zen 6-based "Medusa Point" mobile APUs will not feature RDNA 4 graphics as previously speculated, according to recent code discoveries in AMD GPUOpen Drivers on GitHub. The Device ID "GfxIp12" associated with RDNA 4 architecture has been reserved only for discrete GPUs, confirming that the current Radeon RX 9000 series will exclusively implement AMD's latest graphics architecture. Current technical documentation indicates AMD will instead extend RDNA 3.5 implementation beyond the Zen 5 portfolio while potentially positioning UDNA as the successor technology for integrated graphics.

The chiplet-based Medusa Point design will reportedly pair a single 12-core Zen 6 CCD manufactured on TSMC's 3 nm-class node with a mobile client I/O die likely built on N4P. This arrangement is significantly different from current monolithic mobile solutions. Earlier speculation indicates the Medusa Point platform may support 3D V-Cache variants, leveraging the same vertical stacking methodology employed in current Zen 5 implementations. The mobile processor's memory controllers and neural processing unit are expected to receive substantial updates. However, compatibility limitations with AMD's latest graphics features, like FSR 4 technology, remain a concern due to the absence of RDNA 4 silicon. The Zen 6-powered Medusa Point processor family is scheduled for release in 2026, targeting premium mobile computing applications with a performance profile that builds upon AMD's current Strix Halo positioning.

We have noticed an uptick of AMD Ryzen 9 9950X3D and Ryzen 9 9900X3D-related leaks in mid-to-late February; suggesting an imminent launch. Officially, a Q1 release window was set by Team Red leadership during their CES 2025 presentation, and further disclosures pointed to a loose March window. Earlier today, Golden Pig Upgrade disclosed NDA-busting information—the veteran leaker believes that AMD will be lifting global Ryzen 9 9950X3D CPU review embargoes on March 11. VideoCardz jumped on this unofficial announcement, and reached out to industry insiders. The anonymous contacts reported back; they allege that a March 12 retail release is on the cards.

It is believed that the 16-core and 12-core X3D-equipped "Granite Ridge" Ryzen 9 desktop chips will roll out on the same day (March 12). Coincidentally, Golden Pig Upgrade reckons that Intel's Core Ultra 200HX "Arrow Lake" mobile processor series will launch alongside Team Red's high-end gaming duo. The latter two are touted to attract the majority of press attention on day one. As pointed out by VideoCardz, the release of Radeon RX 9070 GPUs is—speculatively—scheduled a week in advance of AMD's expansion of its Ryzen 9000X3D lineup. Early last week, price points were leaked—courtesy of accidental Newegg listings: $699.99 for the Ryzen 9 9950X3D, and $599.99 for the 12-core Ryzen 9 9900X3D.

AMD is readying two important client segment processors powered by the next-generation "Zen 6" microarchitecture, according to a sensational new report by Moore's Law is Dead. These are the "Medusa Point" mobile processor, and the "Olympic Ridge" desktop. The former is a BGA roughly the size and Z-Height of the current "Strix Point," but the latter is being designed for the existing Socket AM5, making it the third (and probably final) microarchitecture to do so. If you recall, Socket AM4 served three generations of Zen, not counting the refreshed "Zen+." At the heart of the effort is a new CPU complex die (CCD) that AMD plans to use across its client and server lineup.

The "Zen 6" performance CCD is being designed for a 3 nm-class node, likely the TSMC N3E. This node promises a significant increase in transistor density, power, and clock speed improvements over the current TSMC N4P node being used to build the "Zen 5" CCD. Here's where it gets interesting. The CCD contains twelve full-sized "Zen 6" cores, marking the first increase in core-counts of AMD's performance cores since its very first "Zen" CCD. All 12 of these cores are part of a single CPU core complex (CCX), and share a common L3 cache. There could be a proportionate increase in cache size to 48 MB. AMD is also expected to improve the way the CCDs communicate with the I/O die and among each other.

AMD's Ryzen 9000HX lineup of "Fire Range" Zen 5 mobile processors is due for release within a vague March to April window, with the upcoming 3D V-Cache-equipped Ryzen 9 9955HX3D SKU touted to become a top choice for manufacturers of ultra high-end gaming laptops. The latest version of CPU-Z is ready (in advance) with support for Team Red's incoming product line; CPUID's patch notes (published on February 8) have revealed previously unannounced models. AMD's official introduction of Ryzen 9000HX series CPUs included an opening salvo of Ryzen 9 9955HX3D (16-core), 9955HX (16-core) and 9850HX (12-core) models.

According to CPU-Z version 2.14, three additional "Fire Range" SKUs are seemingly on the way. Starting off with the Ryzen 9 9950HX3D—a (presumably) slightly less potent 3D V-Cache-sporting model—its nomenclature suggests that it will sit just below the series flagship. The 9950HX model is expected to slot just under the already announced 9955HX chip. The newly revealed 9845HX SKU could become the lowest 12-core offering within AMD's "Fire Range" product stack.

ASRock has quietly updated its CPU Support List with entries for the upcoming AMD Ryzen 9 9950X3D and 9900X3D desktop processors—starting off with motherboard BIOS versions 3.15 and 3.16. The Taiwanese manufacturer seems to be the very first company to add these "Zen 5" models to public-facing motherboard compatibility databases—according to yesterday evening's VideoCardz report, the likes of MSI, GIGABYTE, and ASUS have not yet followed suit (at the time of writing). The appearance of Team Red's "Granite Ridge" 16-core and 12-core 3D V-Cache-equipped processors on ASRock's website has set off chatter across PC hardware discussion communities.

AMD has not officially revealed a specific launch date (or pricing details) for its Ryzen 9 9950X3D and 9900X3D CPUs—instead, a loose March window has been marked down on this year's calendar. Industry watchdogs believe that ASRock's freshly updated database is proof of an imminent launch—a couple of insiders predicted a January rollout, but this seems unlikely to occur by the end of this working week. Given the reported scarcity of Team Red's already released and highly-praised Ryzen 7 9800X3D gaming processor, many folks will welcome the addition of two alternative options. Team Red has already set expectations for the (presumably) more expensive models—recently, a product manager disclosed that their "new chips will provide similar overall gaming performance" to the current champion.

Intel has launched its first wave of Bartlett Lake processors, introducing hybrid-core models specifically designed for embedded systems, with pure performance-core (P-core) variants scheduled to follow later. The initial release, unveiled at CES, showcases the processors through congatec's new COM-HPC modules. The flagship Core 7 251E leads the embedded lineup with 24 cores (8P + 16E) and impressive clock speeds reaching 5.6 GHz boost. Intel claims this processor outperforms the i7-14700 by 6% in single-core and 8% in multi-core benchmarks, despite maintaining a modest 65 W TDP. The series also includes the Core 5 211E with 10 cores (6P + 4E) and the Core 3 201E featuring 4 P-cores. However, the more intriguing development lies ahead.

Earlier sources indicate that Intel plans to release pure P-core variants of Bartlett Lake in Q3 2025, targeting desktop users. These processors will introduce a more traditional approach by replacing E-core clusters with additional P-cores, resulting in configurations of up to 12 P-cores in the upcoming Core 9 series. The pure P-core models will maintain compatibility with existing LGA1700 motherboards, potentially offering an attractive upgrade path for current Intel platform users. The lineup is expected to include 8-core, 10-core, and 12-core variants under the Core 5, 7, and 9 brands respectively, with TDP options ranging from 45 W to 125 W. While the current embedded models focus on specialized applications like medical imaging and edge computing, the future P-core variants seem positioned to appeal to gamers. The processors are expected to utilize Raptor Cove cores, though rumors suggest Intel might consider backporting Lion Cove architecture to the platform.

AMD today vastly fleshed out its mobile processor lineup with the introduction of two new processor lines besides the Ryzen AI Max 300 series. This includes the introduction of more processor models in the Ryzen AI 300 series that are powered by the "Strix Point" silicon, and the introduction of the Ryzen 200 series mobile processors, which are based on the older "Hawk Point" silicon. In 2024, AMD had debuted the Ryzen AI 300 series "Strix Point," but with just the top-end Ryzen AI 9 370 and 365, which came with maxed out 12-core/24-thread (4x Zen 5 + 8x Zen 5c) core configuration, and a maxed out iGPU with 16 CU. Today the company is introducing the Ryzen AI 7 350, the Ryzen AI 5 340, and their AMD PRO variants for commercial notebooks. Both the consumer and commercial parts have identical specs, except for the latter featuring the AMD PRO feature-set.

The Ryzen AI 7 350 comes with a CPU configuration of 8-core/16-thread (4x Zen 5 + 4x Zen 5c). All cores have a base frequency of 2.00 GHz, the Zen 5 cores boost up to 5.00 GHz. The iGPU on offer is the Radeon 860M, with 12 CU and an engine clock of up to 3.00 GHz. TDP is configurable between 15 W to 55 W. The Ryzen AI 5 340 comes with a 6-core/12-thread configuration (3x Zen 5 + 3x Zen 5c), and CPU clock speeds of 2.00 GHz base with 4.80 GHz boost achievable on the Zen 5 cores. The iGPU is heavily cut down, with just 4 CU available, and an iGPU engine clock of 2.90 GHz. Notebook designers can configure this chip with a wide power range from 15 W to 55 W. All four processor models mentioned above come with a Ryzen AI XDNA 2 NPU that's capable of 50 AI TOPS, which means they're all Microsoft Copilot+ AI PC logo eligible.

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 today expanded its Ryzen 9000X3D line of Socket AM5 desktop processors that combine the "Zen 5" microarchitecture with 3D V-Cache technology, with the introduction of two high core-count models, the Ryzen 9 9950X3D and the Ryzen 9 9900X3D. The 9950X3D is a 16-core/32-thread chip, while the 9900X3D is 12-core/24-thread. These are dual-CCD processors, and much like the Ryzen 9 7000X3D, the 3D V-Cache is only present on one of the two CCDs, while the other is a regular CCD with just the 32 MB on-die L3 cache. There is one key difference, though. Since AMD has redesigned 3D V-Cache for "Zen 5" to be below the CCD and not above, the CCD with it has the same clock speed boosting characteristics as the CCD without 3D V-Cache; and AMD has worked to refine its software-based OS scheduler optimization such that productivity applications favor either of the CCDs, while games stick to the one with 3D V-Cache.

The Ryzen 9 9950X3D comes with a base frequency of 4.30 GHz, and boosts up to 5.70 GHz, with a 170 W TDP. This is much higher than the 5.20 GHz maximum boost frequency of the Ryzen 7 9800X3D, which makes the 9950X3D the company's fastest gaming desktop processor. The Ryzen 9 9900X3D is similarly interesting—you get a base frequency of 4.40 GHz, and 5.50 GHz maximum boost frequency, which is higher than that of the 9800X3D, although the CCD with the 3D V-Cache only has 6 cores. The 9950X3D should hence end up beating the 9800X3D in gaming workloads, while the 9900X3D should be either on par or slightly slower than the 9800X3D at gaming, although faster than any chip from the non-X3D Ryzen 9000 series.

AMD's recently announced Strix Point APU lineup has received favorable reviews from critics and consumers alike. Especially for SFF/Mini PC enthusiasts, Strix Point brings commendable efficiency and performance to the table - both of which are absolutely essential for a high-end mini PC. The GMK EVO-X1 is surely among those, and the system is now available for purchase from GMKTec's official online store.

The EVO X1 sports a 110.19 x 107.3 x 63.2 mm chassis, which is decently compact for its class. As mentioned previously, the system is powered by the 12-core (4x Zen 5 + 8x Zen 5c) Ryzen AI 9 HX 370 APU with the shockingly potent RDNA 3.5-based Radeon 890M iGPU with 16 CUs. For most CPU-centric workloads, the EVO X1 should easily suffice. The iGPU, as mentioned, is potent enough to handle most graphically demanding tasks, including some lightweight gaming, but expecting anything more from it would be futile. Thankfully, an OCuLink port is present, which should allow for extremely fast eGPU connections courtesy of its 64 Gbps bandwidth.

Just recently, we covered a juicy new leak regarding the Geekbench performance of the upcoming Ryzen AI Max+ 395 "Strix Halo" APU. It is no secret that AMD plans on launching the Strix Halo lineup at CES 2025, which happens to be less than a month away. Unsurprisingly, leaked listings of upcoming laptops and other products have been steadily popping up on the internet, with the ASUS ROG Flow Z13 being the rumor mill's latest victim.

As revealed by the product listings by retailers, the ASUS ROG Flow Z13 will indeed pack some truly impressive specifications. Needless to say, the product will feature a variant with the highest-end Ryzen AI Max+ 395 APU with 16 cores and 32 threads, along with an RDNA 3.5-based iGPU with 40 CUs, likely named the Radeon 8060S, which is expected to match mid-range discrete graphics in performance. A slightly lower-tier variant is also listed, with a 12-core Ryzen AI Max 390 APU.