Supermicro Unveils BlueField-4 STX Storage Server for AI Inference
Supermicro has introduced one of the first context memory (CMX) storage servers based on the new BlueField-4 STX reference architecture from NVIDIA, according to a press release.
The BlueField-4 STX platform, announced at NVIDIA GTC 2026, is a modular storage architecture designed for AI workloads that require high-speed data access and scalability. It combines the NVIDIA Vera CPU with the ConnectX-9 SuperNIC and is optimized for AI factories and agentic systems.
Supermicro’s new server builds on its previous Petascale JBOF all-flash array powered by NVIDIA BlueField-3. The CMX storage server aims to accelerate AI inference by keeping data closer to GPUs, improving throughput and efficiency for large-context AI processing.
The company’s BlueField-4 STX system is among the first implementations of NVIDIA’s new architecture, which targets up to five times faster token throughput and up to four times better energy efficiency compared with traditional CPU-based storage designs.
We hope you enjoyed this article.
Consider subscribing to one of our newsletters like Enterprise AI Brief, Silicon Brief or Daily AI Brief.
Also, consider following us on social media:
More from: Enterprise
More from: Data Centers
Subscribe to Enterprise AI Brief
Weekly report on AI business applications, enterprise software releases, automation tools, and industry implementations.
Whitepaper
Governing the Future: A Strategic Framework for AI Adoption in Financial Institutions
This whitepaper explores the transformative impact of artificial intelligence on the financial industry, focusing on the governance challenges and regulatory demands faced by banks. It provides a strategic framework for AI adoption, emphasizing the importance of a unified AI approach to streamline compliance and reduce operational costs. The document offers actionable insights and expert recommendations for banks with fewer than 2,000 employees to become leaders in compliant, customer-centric AI.
Read more