FARAZ
DEContact
Courses

Local AI for companies: keep your data in-house

Run open-weight language models on your own hardware: sizing, Ollama, a team chat with accounts, document Q&A on internal files and an OpenAI-compatible API, secured and documented.

€129one-time payment
Buy the course

Bought it? Sign in with the email from your purchase. Terms · Right of withdrawal

Already enrolled? Sign in

Read the first lesson

Needs a Mac with Apple silicon and at least 16 GB of memory, or a Linux machine with an NVIDIA GPU, plus Docker and basic terminal skills. A server for the team is optional at the start.

Self-study course: slides, hands-on tasks and templates, at your own pace. No graded tests, no individual tutoring.

For whom

Small and mid-sized companies, IT leads and developers who want to use AI on confidential data without sending it to an outside provider.

Where you end up

A local model server with a team chat UI, user accounts, one document collection to ask questions about, an API for your tools and a written security and privacy baseline.

Contents

  1. 01 · Decide and size
  2. 02 · Run models
    • Ollama and llama.cpp: your first local model14 min
    • LM Studio for single workstations10 min
    • Choosing open-weight models and checking licences14 min
  3. 03 · For the team
    • A team chat with Open WebUI15 min
    • Ask your documents: RAG with embeddings15 min
    • An OpenAI-compatible API for your tools and n8n13 min
  4. 04 · Secure and compliant
    • Security: network, accounts, updates, logs14 min
    • GDPR, AI Act and honest limits14 min

Material

  • Hardware sizing sheet with rules of thumb (DE + EN)
  • docker-compose.yml for Ollama + Open WebUI
  • Security and privacy checklist for local AI (DE + EN)

Fabian Faraz Farid · All courses