IIOS · Guide
Deployment Reference Guide
Cloud, hybrid, on-premise, air-gapped, and sovereign models with the trade-offs and controls that shape each choice.
Overview
Deployment Models. Cloud, hybrid, on-premise, air-gapped, and sovereign deployments — with the trade-offs, industries, and controls that shape each choice.
Technology Architecture. The runtime layer: compute, storage, networking, model routing, and local inference that place inference wherever data and latency demand.
Deployment models
Managed Cloud. Fastest to value, elastic scale, fully managed operations. Best fit: Rapid rollout, Elastic analytical workloads, Distributed teams.
Hybrid. Sensitive data and inference stay local; scale bursts to cloud. Best fit: Mixed sensitivity, Gradual migration, Cost/performance balance.
On-Premise. Runs entirely inside your data centers and network. Best fit: Strict residency, Existing data-center investment, OT proximity.
Air-Gapped. No external network connectivity; models and updates delivered offline. Best fit: Classified programs, Critical infrastructure, Highest-assurance sites.
Sovereign. Operated within a national or jurisdictional boundary you define. Best fit: National programs, Regulated data, Public-sector mandates.
Learn more
This reference summarizes material covered in full across the Architecture Center. For the complete treatment, see Deployment Models, and Technology Architecture.