Autoplay
Autocomplete
Previous Lesson
Complete and Continue
Local AI Revolution: Ollama and OpenClaw
Introduction
Introduction to the Local AI Revolution (4:34)
Exercise: Meet Your Classmates and Instructor
Course Resources
Private AI: Ollama + Open Source Models From Scratch
DigitalOcean Sign Up and SSH Setup (4:08)
Create the Droplet and Set Up Your User (8:39)
Install and Configure Ollama (7:04)
Where to Find Ollama Models: Ollama Library, Hugging Face, GGUF, and Model Tags (6:38)
Pull Models and Run Your First Inference (11:38)
Parameters, Quantization, and VRAM: Why Models Are the Size They Are (11:58)
Adjusting Model Behaviour in the Interactive Shell (7:19)
Saving and Reusing Model Configurations (6:31)
Customizing Models with Modelfile (7:54)
ChatGPT-Like Interface for Your Private AI: Open WebUI Setup (7:19)
Access Your AI Securely From Anywhere: SSH Tunneling Explained (8:14)
LM Studio: A Desktop Alternative to Ollama (5:18)
GPU Inference on Vast.ai + OpenClaw: 20× Faster, Same Stack
Introduction: From CPU to GPU (3:34)
Sign Up on Vast.ai and Add Your SSH Key (4:43)
Deploy a GPU Instance and Connect (7:24)
Install and Configure Ollama (7:26)
Pull Models and Manage the Instance (7:15)
CPU vs GPU - Live Benchmark (5:13)
What Is Agentic AI? The Shift From Chatbots to Autonomous Agents (8:21)
Install and Configure OpenClaw (6:38)
Session Startup and Terminal Multiplexing (11:25)
Connect Telegram to OpenClaw (8:21)
OpenClaw Config: Telegram Hardening (4:02)
Where To Go From Here?
Review This Byte!
Become An Alumni
Pull Models and Run Your First Inference
This lecture is available exclusively for ZTM Academy members.
If you're already a member,
you'll need to login
.
Join ZTM To Unlock All Lectures