Courses & Learning

Local AI Models

Flavio Copes' free 34-lesson course on open-weight models, choosing a model that fits your hardware, running it locally with Ollama and Node.js, building a private AI feature with structured output and fallbacks, and operating local AI responsibly.

Curriculum

5 modules · 34 lessons

1

Understand open weights

Separate weights, architecture, training, inference, licenses, and the wider meaning of open source AI.
1. 01 Weights are learned numbers
2. 02 Separate training from inference
3. 03 Architecture, weights, and runtime
4. 04 Open weights and open source AI
5. 05 Read the model card and license
6. 06 Check your understanding: open weights
2

Choose a model that fits

Compare capabilities, parameter counts, quantization, formats, context, memory, and task quality.
1. 07 Start from the task
2. 08 Parameters and memory
3. 09 Understand quantization
4. 10 Safetensors and GGUF
5. 11 Context and the KV cache
6. 12 Build a small evaluation
7. 13 Check your understanding: choosing a model
3

Run models locally

Install Ollama, manage model files, use the local API, stream responses, and measure performance.
1. 14 Choose a local runtime
2. 15 Install and check Ollama
3. 16 Pull and run your first model
4. 17 Call the local chat API
5. 18 Call Ollama from Node.js
6. 19 Stream and measure responses
7. 20 Check your understanding: running models locally
4

Build a local AI feature

Create a Node.js summarizer with structured output, timeouts, cancellation, fallback behavior, and focused tests.
1. 21 Define the feature boundary
2. 22 Request structured output
3. 23 Add timeout and cancellation
4. 24 Add a deterministic fallback
5. 25 Use tools with a permission boundary
6. 26 Keep the provider swappable
7. 27 Test the local AI feature
8. 28 Check your understanding: building a local feature
5

Operate local AI responsibly

Review privacy, model supply chains, permissions, upgrades, costs, evaluations, and production boundaries.
1. 29 Map the complete data flow
2. 30 Verify model files and code
3. 31 Pin and upgrade models
4. 32 Understand the real cost
5. 33 Complete the local summarizer
6. 34 Check your understanding: operating local AI