CXMT unveils homegrown DDR5-8000 and LPDDR5X-10667 memory

Chinese memory maker CXMT unveiled its first homegrown DDR5-8000 and LPDDR5X-10667 modules at the 2025 China International Semiconductor Expo, targeting servers and Artificial Intelligence workloads. Speeds reach 8,000 MT/s for DDR5 and 10,667 MT/s for LPDDR5X, with module capacities and packaging aimed at data centers, desktops and laptops.

CXMT showcased its first homegrown high-speed memory modules at the 2025 China International Semiconductor Expo, introducing DDR5-8000 and LPDDR5X-10667 products. The company positioned these modules as its most advanced offerings to date, claiming performance on par with major competitors such as Samsung, SK Hynix and Micron. CXMT presented the announcement in the context of China ramping up server infrastructure for traditional computing and Artificial Intelligence, while noting constraints tied to domestic silicon production capabilities.

Technical details released by CXMT list operating speeds of 8,000 MT/s for DDR5 and 10,667 MT/s for LPDDR5X. The company offered capacity options of 12 Gb and 16 Gb for LPDDR5X and 16 Gb and 24 Gb formats for DDR5. The announcement also referenced comparable offerings from Samsung, including LPDDR6, which the company notes reaches a top LPDDR5X-equivalent speed of about 10,700 MT/s. CXMT framed its modules as competitive with the latest international chips in raw transfer rates.

CXMT described multiple module and packaging targets for the new parts. Server and enterprise configurations will use RDIMM, MRDIMM and TFF MRDIMM formats. Mainstream desktops and PCs are served by UDIMM modules while laptops and compact devices will use SODIMM. The company also highlighted clock drive modules, including CUDIMM and CSODIMM, aimed at high-end overclocking and workstation markets. In particular the server market was identified as the largest segment, with CXMT RDIMMs offered in a range of capacities to cover mainstream platform memory configurations.

55

Impact Score

Inside the UK’s artificial intelligence security institute

The UK’s artificial intelligence security institute has found that popular frontier models can be jailbroken at scale, exposing reliability gaps and security risks for governments and regulated industries that rely on trusted vendors.

Siemens debuts digital twin composer for industrial metaverse deployments

Siemens has introduced digital twin composer, a software tool that builds industrial metaverse environments at scale by merging comprehensive digital twins with real-time physical data, enabling faster virtual decision making. Early deployments with PepsiCo report higher throughput, shorter design cycles and reduced capital expenditure through physics-accurate simulations and artificial intelligence driven optimization.

Cadence builds chiplet partner ecosystem for physical artificial intelligence and data center designs

Cadence has introduced a Chiplet Spec-to-Packaged Parts ecosystem aimed at simplifying chiplet design for physical artificial intelligence, data center and high performance computing workloads, backed by a roster of intellectual property and foundry partners. The program centers on a physical artificial intelligence chiplet platform and framework that integrates prevalidated components to cut risk and speed commercial deployment.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.