Intermediate
Local LLM Stack
A track on a private AI stack. Running models locally via Ollama and LM Studio, choosing hardware, working with documents via RAG, open-source models.
10 hours3 courses~2 weeks
Courses in track
Follow them in order — the sequence is intentional. You can also go non-linearly if you know what you're doing.
01Local LLM: Ollama, LM Studio, private stack
IntermediateA course on running models locally. Why, how, what to pick for your hardware, and how to use it in production.
02RAG and working with documents
IntermediateA course on Retrieval Augmented Generation: when you need it, how to build it, where it breaks.
03DeepSeek, Qwen, Mistral, and Open-Source Models
IntermediateA course on open-weight models: where they're already comparable to the flagships, where they aren't, and how to apply them.
What you'll be able to do
Specific skills and scenarios you'll have after completing the track.
01Write prompts confidently and get predictable results
02Choose the right model for each task instead of using one for everything
03Recognize where AI genuinely helps versus where it slows you down
04Build working workflows with minimal automation overhead
05Understand LLM limitations and avoid brittle system design
06Integrate AI into daily work without resistance or chaos
Good fit
- You are engineers, privacy-sensitive teams, the legal/medical segment
- Ready to spend ~30 minutes a day
- Want concrete skills, not just a market overview
Not a fit
- If you're looking for 'make money with ChatGPT in 7 days'
- If you want ready-made answers without practice
- If you're already at an advanced level