# Air-Gapped AI - Local Models, Maximum Control for K-12 > Source: https://ibl.ai/service/air-gapped-ai/k12 Run ibl.ai's entire Agentic OS on air-gapped Ubuntu servers with NVIDIA GPUs. Local models via NIM, Ollama, or vLLM. Zero external API calls, complete data sovereignty for your district. Deploy ibl.ai's full Agentic OS on air-gapped infrastructure where no student data ever leaves your district network. Models run locally on Ubuntu servers with NVIDIA GPUs via NIM, Ollama, or vLLM. ibl.ai's forward-deployed engineers install the entire stack on your hardware. You get the same AI agent capabilities as our cloud deployment—tutoring, teacher support, administrative automation—with zero external API calls and complete data sovereignty. ## What This Is ### Air-Gapped AI is ibl.ai's on-premise deployment option. The entire Agentic OS—agent runtime, model serving, vector databases, orchestration layer—runs on Ubuntu servers inside your district network with no internet connectivity required after initial setup. Models are served locally through NVIDIA NIM, Ollama, or vLLM on your NVIDIA GPUs. You choose from models by NVIDIA, Meta (Llama), Google (Gemma), Microsoft (Phi), Mistral, and others. Every inference request stays within your security perimeter. ibl.ai's forward-deployed engineers configure the stack, optimize model performance for your hardware, integrate with your district systems, and transfer full operational knowledge to your team. Every configuration file, every model weight, every integration adapter belongs to your district. ## Why Air-Gapped for K-12 ### Complete Student Data Protection No student data leaves your network. No API calls to OpenAI, Anthropic, Google, or any external service. Student records, assessments, and interactions stay within your district's security perimeter. ### COPPA/CIPA/FERPA by Architecture Air-gapped deployment eliminates third-party data processing agreements. Student data never crosses a network boundary. Compliance is built into the architecture, not bolted on through contracts. ### Parent and Community Trust Demonstrate to parents and school boards that student data stays on district-owned hardware. No vendor has access to student interactions. Full transparency about where data lives and how it is used. ### Model Choice and Flexibility Run any open model that fits your GPUs. Switch between Llama, Gemma, Phi, Mistral, or NVIDIA NeMo models without changing agent configurations. No vendor lock-in to any single model provider. ### Same Capabilities as Cloud Air-gapped deployment runs the full ibl.ai Agentic OS. AI tutors, teacher assistants, course generation, analytics—every feature works identically to the cloud version. ## Supported Models and Inference Engines ### NVIDIA NIM GPU-optimized inference microservices for maximum throughput on NVIDIA hardware. Supports Llama, Mistral, and NVIDIA NeMo models with TensorRT-LLM acceleration. Best for high-throughput production workloads. ### Ollama Lightweight model serving for rapid deployment and testing. Supports a broad catalog of open models with simple configuration. Ideal for development environments and smaller-scale deployments. ### vLLM High-performance inference engine with PagedAttention for efficient memory management. Supports continuous batching for maximum GPU utilization. Production-grade serving for large-scale deployments. ### Model Catalog Meta Llama (8B, 70B, 405B), Google Gemma (2B, 7B, 27B), Microsoft Phi (3.5, 4), Mistral (7B, 8x7B, Large), NVIDIA NeMo models, and any Hugging Face-compatible model. New models added as they release. ## Infrastructure Requirements ### Operating System Ubuntu 22.04 LTS or later. Standard server installation with NVIDIA drivers and CUDA toolkit. No specialized OS or kernel modifications required. ### GPU Requirements NVIDIA GPUs with sufficient VRAM for your chosen models. A single A100 80GB runs Llama 70B. Smaller models like Phi-3.5 or Gemma 7B run on consumer-grade GPUs. We right-size recommendations to your workload. ### Network No internet connectivity required after initial setup. Internal network access to district systems (SIS, LMS, SSO) for integrations. All model weights and dependencies are pre-loaded during installation. ### Storage SSD storage for model weights, vector databases, and agent state. Capacity depends on the number of models deployed. Typical installations require 500GB to 2TB of fast storage. ## Security and Compliance ### COPPA Compliant No student data is collected or processed by external services. All AI interactions happen on district hardware. Parental consent requirements are simplified when no third parties are involved. ### CIPA Aligned Content filtering and age-appropriate guardrails run locally. No student queries are sent to external APIs for moderation. Your district controls every content policy. ### FERPA by Default Student educational records stay on your infrastructure. No third-party data processing. Audit logs capture every agent interaction locally for compliance reporting. ### State Privacy Laws Air-gapped deployment meets the strictest state student privacy laws. No data sharing with vendors. No cloud subprocessors. Your district maintains sole custody of all student data. ## Deployment Options ### Single Server Entire stack on one Ubuntu server with NVIDIA GPUs. Suitable for individual schools or pilot programs. Simple to operate and maintain. ### Multi-Node Cluster Distributed deployment across multiple servers for higher throughput and redundancy. Kubernetes orchestration with Helm charts. Scales to district-wide usage. ### Hybrid (Air-Gapped + Cloud) Sensitive workloads on air-gapped servers, general-purpose agents on ibl.ai cloud. Consistent agent configurations across both environments. Migrate workloads as policies evolve. ## What You Own ### Complete Agentic OS installation on your hardware with all agent configurations and model settings documented ### Local model weights for all deployed models—pre-downloaded and optimized for your GPU hardware ### Inference engine configurations (NIM, Ollama, or vLLM) tuned for your specific hardware and workload ### District system integration adapters (SIS, LMS, SSO) with full source code ### Infrastructure as Code (Ansible/Helm) for repeatable deployments and disaster recovery ### Operational runbooks covering model updates, GPU monitoring, backup procedures, and troubleshooting ### Security documentation for your compliance team—architecture diagrams, data flow maps, control matrices ## Engagement Model ### Infrastructure Assessment (1 week): Evaluate your server hardware, GPU inventory, network topology, and integration requirements. Right-size model recommendations to your district's compute capacity. ### Installation and Configuration (2-4 weeks): Forward-deployed engineers install the Agentic OS, configure inference engines, load model weights, build district integrations, and validate the full stack in your environment. ### Agent Development (2-3 weeks): Build your first set of AI agents—subject tutors, teacher assistants, administrative aids. Configure content safety guardrails, knowledge bases, and tool integrations for your curriculum. ### Knowledge Transfer (1-2 weeks): Train your technology team on model management, agent configuration, GPU monitoring, and operational procedures. Your team operates independently after handoff. ## Get Started ### Hardware Assessment: Free 30-minute session to evaluate your existing infrastructure and recommend a deployment configuration for your district. ### Proof of Concept: Deploy the Agentic OS on a single server with one or two agents to validate the approach before committing to district-wide deployment. ### District Deployment: Complete air-gapped installation with district integrations, agent library, operational documentation, and knowledge transfer. --- *[View on ibl.ai](https://ibl.ai/service/air-gapped-ai/k12)*