📁 Hardware

ZimaBoard 2 is a Linux mini server powered by the Intel N150 processor, designed for small office or home use. Preloaded with ZimaOS, a Linux-based "personal cloud OS", it simplifies hosting services for SOHO needs. Its aluminum chassis and connectivity options make it an interesting solution for those seeking a low-power server.

A motherboard buying guide based on benchmarks and thorough testing. The article analyzes critical components and suggests how to allocate budget for maximum performance, highlighting areas where savings are possible without compromising overall system efficiency.

AMD is preparing new performance optimizations for its processors, introducing a feature called CPPC Performance Priority. Patches submitted to the Linux kernel mailing list suggest this hardware feature will be implemented with future Zen 6 processors, promising improvements in resource management and energy efficiency.

A user shared their experience optimizing the Qwen3.5 122B A10B model on consumer hardware, highlighting the importance of manual tensor fitting and BF16 cache to improve performance and stability. The results show a significant increase in processing speed compared to automatic settings, but with some limitations in agentic use.

Apple's new MacBook Neo is rumored to feature the A18 Pro chip, a decision partly driven by supply chain constraints. This strategic move could redefine Apple's entry-level laptop segment, offering high performance at a competitive price point.

Samsung has announced faster-than-expected progress in the production of 2nm chips. The company aims to triple its revenue from HBM (High Bandwidth Memory), which is crucial for artificial intelligence and high-performance computing applications.

Apple has removed the 512GB memory configuration of the Mac Studio from its website. It is unclear whether this is a temporary suspension in anticipation of a product refresh or a definitive decision due to DRAM scarcity.

NVIDIA has released the beta version of the R595.45.04 drivers for Linux, following the release of the R595 drivers for Windows. This new version introduces enhancements to Vulkan support and DRI3 v1.2, potentially offering benefits for those using NVIDIA GPUs in Linux environments, particularly for high-performance graphics and compute workloads.

AMD is staging improvements to the AMDGPU and AMDKFD kernel drivers for the upcoming Linux 7.1 cycle. The updates primarily focus on the integration of DCN 4.2 IP and GFX 12.1, with a particular emphasis on support for GCN 1.1 APUs.

Rumors suggest Nvidia is developing the RTX 5050 with 9GB of GDDR7 VRAM on a 96-bit bus, alongside an RTX 5060 with a cut-down GB205 GPU. The new cards could target entry-level market segments, offering a more accessible option for consumers.

Despite initial issues with open-source drivers, Intel's GMA500 driver, created to support PowerVR SGX graphics hardware (code-named Poulsbo), continues to receive updates in the Linux kernel, almost twenty years after its introduction. An example of persistence in the open-source world.

An international team has created a high-resolution 3D atlas of ant morphology, called Antscan. Using a particle accelerator, researchers digitized 792 ant species, making detailed 3D models of exoskeletons, muscles, and internal organs accessible online. This resource opens new perspectives for scientific research, education, and engineering.

Micron has announced SOCAMM2, a new 256GB memory module designed for AI servers. The new technology allows scaling memory up to 2TB per CPU, enhancing the performance of artificial intelligence applications. This solution is particularly relevant for workloads requiring high memory capacity and bandwidth.

Broadcom will soon deploy multiple gigawatts worth of custom accelerators at Meta, OpenAI, and Anthropic. The company argues this shows that AI companies and hyperscalers can’t successfully develop and deploy their own silicio any time soon.

Broadcom and TSMC are collaborating on chips for artificial intelligence applications, leveraging 3.5D integration. This strategic move could position Broadcom as a direct competitor to Nvidia in the high-performance ASIC (Application-Specific Integrated Circuit) market, offering new options for AI workloads.

Intel is preparing support for the Xe3P graphics architecture in the Mesa OpenGL "Iris" and Vulkan "ANV" open-source drivers. This follows the enablement of Xe3P in the mainline Linux kernel for upcoming Nova Lake integrated graphics and the Crescent Island AI inference accelerator.

The Linux Foundation introduced the OCUDU Ecosystem Foundation at Mobile World Congress (MWC). This initiative aims to advance open-source AI-RAN (Radio Access Network) innovation for 5G and early 6G network solutions. Early performance tests on AMD EPYC and Intel Xeon server platforms indicate an initial lead for AMD EPYC.

The new Nvidia driver 595.71 appears to introduce overclocking limitations on some GeForce graphics cards, particularly the RTX 40 and 50 series. Not all GPUs are affected, but the driver release seems problematic for those aiming to maximize hardware performance.

Nvidia has entered into multi-year agreements with Lumentum and Coherent, marking a significant step forward in the commercialization of silicio photonics. These collaborations could optimize high-speed interconnects, crucial for future accelerated computing architectures and artificial intelligence workloads.

The US Department of Defense is reverse-engineering Iranian-made Shahed drones. The goal is to better understand asymmetric warfare tactics and develop countermeasures, particularly through the use of AI-controlled drone swarms within the LUCAS project.