Skip to content
NerdLevelTech
Intermediate

Local LLM Development with Ollama

Master running large language models locally with Ollama. Learn to deploy open-source models, integrate with LangChain/LangGraph, build local RAG pipelines, and optimize performance for production.

66 min22 lessons6 modulesAI & ML

What you'll learn

  • Explain the benefits and tradeoffs of local LLM deployment
  • Install and configure Ollama on any platform
  • Run and customize open-source models like Llama 3/4, Mistral, Qwen, and Phi
  • Build Python applications using Ollama's REST API and SDK
  • Integrate local models with LangChain and LangGraph
  • Create fully local RAG pipelines with local embeddings
  • Implement function calling with local models
  • Optimize performance through quantization and hardware configuration
  • Deploy Ollama in production with Docker and scaling strategies

Course Content

  1. Why Local LLMs?

    3 lessons · 10 min

  2. Ollama Fundamentals

    4 lessons · 12 min
    • Locked until you enrollInstalling Ollama3 min
    • Locked until you enrollRunning Your First Model3 min
    • Locked until you enrollOllama CLI Mastery3 min
    • Locked until you enrollModel Customization3 min
    • Quiz: Module 2: Ollama Fundamentals

  3. Building Applications with Ollama

    4 lessons · 12 min
    • Locked until you enrollOllama API Basics3 min
    • Locked until you enrollPython Integration3 min
    • Locked until you enrollLangChain with Ollama3 min
    • Locked until you enrollLangGraph with Ollama3 min
    • Quiz: Module 3: Building Applications with Ollama

  4. Advanced Local LLM Patterns

    4 lessons · 12 min
    • Locked until you enrollLocal Embeddings3 min
    • Locked until you enrollLocal RAG Pipeline3 min
    • Locked until you enrollFunction Calling Locally3 min
    • Locked until you enrollMulti-Model Workflows3 min
    • Quiz: Module 4: Advanced Local LLM Patterns

  5. Performance & Optimization

    4 lessons · 12 min
    • Locked until you enrollHardware Requirements3 min
    • Locked until you enrollQuantization Explained3 min
    • Locked until you enrollPerformance Tuning3 min
    • Locked until you enrollvLLM for Production3 min
    • Quiz: Module 5: Performance & Optimization

  6. Production Deployment

    3 lessons · 8 min
    • Locked until you enrollDocker Deployment3 min
    • Locked until you enrollScaling Local Inference3 min
    • Locked until you enrollNext Steps2 min
    • Quiz: Module 6: Production Deployment