Ollama Courses and Certifications

Ian Wootten

Using Ollama to Run Local LLMs on the Steam Deck - Performance Comparison with Raspberry Pi 5

Explore running Ollama's local LLMs on Steam Deck: installation process, model performance, and comparison with Raspberry Pi 5 speeds in this hands-on tutorial.

• YouTube
• 11 minutes
• On-Demand
• Free Video

Ian Wootten

Code Llama: First Look and Python Coding Challenges - Ollama Setup

Explore Code Llama's capabilities through installation, comparison with Llama 2, and Python coding challenges in this hands-on walkthrough using Ollama on Mac.

• YouTube
• 12 minutes
• On-Demand
• Free Video

Eli the Computer Guy

AI and Python - Ollama for Local LLM AI Usage

Learn to run LLMs locally with Ollama, from installation to Python integration. Explore various models, command-line usage, and script connections for AI-powered applications without relying on external APIs.

• YouTube
• 2 hours 27 minutes
• On-Demand
• Free Video

Eli the Computer Guy

DIY AI-Powered Autoblog with Ollama, Llama2, Python, and Bottle

Learn to create an AI-powered autoblog using Ollama, Llama2, Python, and Bottle. Rewrite existing blog content with LLM technology and store it in a database.

• YouTube
• 34 minutes
• On-Demand
• Free Video

Eli the Computer Guy

Ollama and Python for Local AI LLM Systems

Learn to set up and use Ollama with Python for local AI language models, including installation, model management, and integration techniques.

• YouTube
• 30 minutes
• On-Demand
• Free Video

JSConf

Privacy-Friendly Applications with Ollama, Vector Functions, and LangChainJS

Explore building privacy-focused AI applications using Ollama for local LLMs, vector functions for efficient searches, and LangChainJS for versatile agents, ensuring data stays on your device.

• YouTube
• 29 minutes
• On-Demand
• Free Video

Decoder

Building a Chat App with Ollama-py and Streamlit in Python

Build a Python chat app using Ollama-py and Streamlit. Learn to implement key features like user input, message history, model selection, and streaming responses.

• YouTube
• 22 minutes
• On-Demand
• Free Video

Sam Witteveen

Building a Vision App with Ollama Structured Outputs

Discover how to leverage Ollama structured outputs for named entity recognition and image analysis while building a practical vision application from scratch.

• YouTube
• 18 minutes
• On-Demand
• Free Video

Venelin Valkov

DeepSeek-R1 0528 for 100% Local Chat with Your Files - Financial Document Analysis AI with Ollama

Master private financial document analysis using DeepSeek-R1 locally with Ollama, comparing performance against cloud AI models through hands-on PDF processing.

• YouTube
• 25 minutes
• On-Demand
• Free Video

ByteGrad

Self-Host AI on VPS with Ollama and OpenWebUI

Discover how to easily deploy AI models on a VPS using Ollama and OpenWebUI, from local setup to cloud hosting with practical implementation steps.

• YouTube
• 15 minutes
• On-Demand
• Free Video

Eli the Computer Guy

Intro to AI LLM Systems with Ollama and Python

Master building custom AI systems using Ollama and Python, from local LLM setup to web apps with databases, creating competitive advantages without subscription fees.

• YouTube
• 2 hours 31 minutes
• On-Demand
• Free Video

Venelin Valkov

Creating a Private Local AI Assistant with DeepSeek-R1 and Ollama for Document Chat

Learn to build a private AI assistant using DeepSeek-R1 and Ollama for secure, offline document analysis and chat interactions with local files, featuring Streamlit UI integration.

• YouTube
• 19 minutes
• On-Demand
• Free Video

Tech with Tim

EASIEST Way to Fine-Tune a LLM and Use It With Ollama

Master the simplest method to fine-tune large language models in Python and deploy them using Ollama, with step-by-step guidance and complete code examples.

• YouTube
• 22 minutes
• On-Demand
• Free Video

Jeff Heaton

Set Up Your Own LLM Server at Home - Run Local AI Models with Ollama and NVIDIA DGX Spark

Discover how to deploy Ollama on NVIDIA DGX Spark to run 70B+ parameter models locally with Docker, WebUI access, and OpenAI-compatible Python integration for your own AI applications.

• YouTube
• 11 minutes
• On-Demand
• Free Video

Data Centric

Running Local LLMs Faster Than Ollama Using Llamafile

Master running local LLMs with Llamafile, achieving 30-500% faster performance than Ollama on CPU. Learn to convert models into executable files and optimize your machine learning workflow.

• YouTube
• 12 minutes
• On-Demand
• Free Video