Bare-metal Instances Overview

Wed, 01 Jul 2026 00:00:00 +0000

Metal Instances extend OpenNebula workload operation to dedicated physical servers, allowing cloud users and operators to consume bare-metal resources through controlled, automated service workflows. They are designed for environments where workloads need direct access to the underlying hardware, predictable performance, strong isolation, or specialized acceleration devices.

This model is particularly useful for AI Factory, HPC, edge, sovereign cloud, and service-provider environments, where virtualized infrastructure may not always provide the required level of hardware control or performance. Metal Instances make it possible to manage these resources as part of a broader OpenNebula cloud, while preserving the benefits of automation, multi-tenancy, capacity control, and operational consistency.

Bare Metal as a Service with NVIDIA Infra Controller (AI)

Wed, 24 Jun 2026 00:00:00 +0000

This guide describes how to integrate an existing OpenNebula cloud with the NVIDIA Infra Controller (NICo) to offer basic multi-tenant Bare Metal as a Service. OpenNebula represents each NICo allocation as a Host and uses the NICo Virtual Machine Manager (VMM) and Information Manager (IM) drivers to create, monitor, and delete bare-metal instances through the NICo REST API.

This integration is intended for environments where OpenNebula provides cloud management, user, group, quota, and template controls, while NICo provides the bare-metal capacity and lifecycle operations for each instance.

Metal Instances (AI) on

Bare-metal Instances Overview

Bare Metal as a Service with NVIDIA Infra Controller (AI)