Run powerful models on your own hardware or ultra-fast Groq inference engines.
Schedule
July 25 - August 1, 2026
Duration
2 weeks • 2hrs/wk
Project
Hands-on capstone
4 practical sections built around live exercises.
Install, run, and manage open models locally.
Topics covered
Hands-on lab
Run a local model and compare output, latency, and memory use across model sizes.
Tune local models for specific tasks and constraints.
Topics covered
Hands-on lab
Create a custom Ollama model profile for a focused assistant.
Use Groq when speed matters and understand when cloud inference is the better path.
Topics covered
Hands-on lab
Build a small script that can switch between local Ollama and Groq-backed inference.
Design apps that keep sensitive workflows close to your machine or private infrastructure.
Topics covered
Hands-on lab
Design a private assistant for one sensitive document or business workflow.
Concrete capabilities you should leave with.
Run and customize local models with Ollama
Understand quantization and hardware limits
Use Groq for fast hosted inference
Design privacy-first AI workflows