Eoptolink Introduces 12.8T Liquid-Cooled Optical Module for AI Data Centers

March 16, 2026
Eoptolink Technology Inc., Ltd. has launched its 12.8T XPO optical transceiver, an industry-first liquid-cooled pluggable module designed to support high-density AI data center networks, and joined the XPO Multi-Source Agreement as a founding member.

Eoptolink Technology Inc., Ltd. has introduced its 12.8T XPO pluggable optical transceiver, an industry-first liquid-cooled module for AI data centers, announced in a press release. The module is designed to support scale-up, scale-out, and metro-reach architectures, delivering 12.8 Tbps throughput through 64 lanes operating at 200 Gbps each.

The XPO achieves a front-panel density of 204.8 Tbps in a 4-RU rack, offering four times the capacity of current 1.6T OSFP solutions. It integrates a cold plate capable of cooling up to 400W per module, ensuring stable performance under high-power conditions. The design also supports linear, half-retimed, and fully-retimed interfaces, providing flexibility for deployment.

Eoptolink has joined the XPO Multi-Source Agreement (MSA) as a founding member. The consortium focuses on developing high-density, liquid-cooled pluggable optics for next-generation AI and cloud data center infrastructure. The company is showcasing the 12.8T XPO alongside its 400G/lambda-1.6T and 200G/lambda-1.6T optical transceiver series at OFC 2026 in Los Angeles.

We hope you enjoyed this article.

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)

More from: Data Centers

03/16
RadiusDC to Acquire phoenixNAP’s Phoenix Data Center and Colocation Business
03/16
Hans Vestberg Co-Founds Next Phase of US Data Centers with Digi Power X
03/16
Core AI Holdings and Optimus Tech Form OptiCore Datacenters for U.S. Research Universities
03/16
AWS and Cerebras Partner to Deliver Fastest AI Inference on Bedrock
03/16
Pure Data Centres and AVK Deploy Europe’s First 110 MW Data Center Microgrid in Dublin

Subscribe to Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

AI Token Webinar

Market report

AI’s Time-to-Market Quagmire: Why Enterprises Struggle to Scale AI Innovation

ModelOp

The 2025 AI Governance Benchmark Report by ModelOp provides insights from 100 senior AI and data leaders across various industries, highlighting the challenges enterprises face in scaling AI initiatives. The report emphasizes the importance of AI governance and automation in overcoming fragmented systems and inconsistent practices, showcasing how early adoption correlates with faster deployment and stronger ROI.

Read more

You May Also Like