HPCwire reports that Nutanix and Supermicro have jointly engineered a system for private inference to tackle runaway AI costs.
BERLIN, Oct. 23, 2026 — Nutanix and Super Micro Computer, Inc. have announced plans for a jointly engineered AI infrastructure solution, powered by Nutanix Agentic AI, that is designed to help enterprises take on runaway AI costs with a system for private inference.
Built on validated Supermicro systems powered by Nutanix Agentic AI, the solution will combine the Nutanix Cloud Platform with Supermicro servers, NVIDIA GPUs, and NVIDIA Spectrum-X networking. It is designed to reduce custom configuration and integration complexity and to simplify the path from infrastructure deployment to production-ready AI. Nutanix offers a complete, full-stack AI platform engineered to simplify and accelerate the deployment of enterprise AI workloads, from the underlying infrastructure through model execution to the governance of agentic workloads.
The solution will enable seamless provisioning from bare metal to integrated model-as-a-service and a secure Agent Gateway, using the Nutanix Kubernetes Platform, a Cloud Native Computing Foundation-certified, AI-conformant Kubernetes distribution, and Nutanix Enterprise AI. It will be supported by Nutanix Unified Storage (NUS), which provides high-performance, NVIDIA Enterprise-certified storage for AI workloads, including context caching and model serving. Together, these capabilities are intended to provide the end-to-end performance, resilience, and orchestration required to support modern AI initiatives. A built-in AI catalog will further simplify deployment by providing access to common AI applications.
As AI requirements grow, the architecture is designed to scale GPU capacity, while the dedicated Nutanix control plane and storage services support resilient operations and high-throughput data workflows. With this engineered offering, customers will be able to more easily deploy, manage, and scale AI inference workloads without having to assemble and connect a complex mix of multivendor technologies.
"Collaborating with Nutanix, we want to accelerate time-to-online for enterprise AI," said Matthew Thauberger, Chief Revenue Officer, Supermicro. "Combining Supermicro's engineered servers with Nutanix's full-stack software will deliver a pre-validated, rack-scale solution that bypasses traditional lead-time delays. It will help give organizations predictable access to high-density GPU compute while removing the operational complexity of scaling AI."
"Moving AI from experimentation into production remains a challenge for many enterprises, with infrastructure complexity and hardware procurement often slowing progress. Our expanded collaboration with Supermicro is a direct response to this barrier," said Thomas Cornely, Executive Vice President, Product Management, Nutanix. "The Supermicro systems, engineered with our Nutanix Agentic AI full stack software, will help enterprises simplify how AI infrastructure is deployed, operated, secured, and scaled, enabling them to simply deploy private inference and control the cost per token as AI adoption scales."
**Reducing the Complexity of Enterprise AI Infrastructure**
The engineered solution is intended to provide a hardware foundation that helps eliminate custom-order delays. It uses Supermicro server systems that house eight NVIDIA Blackwell Ultra GPUs per node.
The resilient, single-tenant control plane is expected to feature a dedicated Nutanix management cluster (NX-8170-G10), which protects against management plane failure without disrupting GPU execution.
For high-performance storage scaling, an integrated NUS cluster (NX-8150-G10) is optimized for the high-bandwidth I/O requirements of AI data ingestion, checkpointing, and cache warming.
NVIDIA Spectrum-X Ethernet networking combines NVIDIA Spectrum-4 Ethernet switches (SN5610/SN5600) with NVIDIA ConnectX-7/8 SuperNICs for high-performance, predictable GPU-to-GPU scale-out connectivity. It also includes NVIDIA BlueField-3 DPUs for infrastructure offloading and in-band management, complementing NVIDIA's scale-in networking architecture.
**Availability**
The Supermicro systems powered by Nutanix Agentic AI will be available in early 2027 from Supermicro and its channel partners.
**About Nutanix**
Nutanix (NASDAQ: NTNX) is a hybrid cloud leader and AI platform company, offering organizations a unified infrastructure software platform to safely run applications, data, and AI anywhere. Trusted by customers worldwide, Nutanix empowers more than 50% of the Global 2000 to innovate faster with AI, while modernizing infrastructure, simplifying operations, and controlling costs.
**About Super Micro Computer, Inc.**
Supermicro (NASDAQ: SMCI) is a global leader in Application-Optimized Total IT Solutions. Founded and headquartered in San Jose, California, Supermicro is committed to delivering first-to-market innovation for Enterprise, Cloud, AI, and 5G Telco/Edge IT Infrastructure. As a Total IT Solutions provider, it offers server, AI, storage, IoT, switch systems, software, and support services. Supermicro's motherboard, power, and chassis design expertise further enables its development and production, supporting next-generation innovation from cloud to edge for global customers. Its products are designed and manufactured in-house (in the US, Taiwan, and the Netherlands), leveraging global operations for scale and efficiency and optimized to improve TCO and reduce environmental impact (Green Computing). The award-winning Server Building Block Solutions portfolio allows customers to optimize for their exact workload and application by selecting from a broad family of systems built from flexible, reusable building blocks. These support a comprehensive set of form factors, processors, memory, GPUs, storage, networking, power, and cooling solutions (air-conditioned, free air cooling, or liquid cooling).