Updated Hardware Recommendations for Running AI Locally (March 2026)
Update to: [ DIY
LocalAI
Is It Just Semantics about Gen AI and Privacy?
Over on Mastodon, PLB (initials only, although you can read the conversations via Mastodon ) makes this point: My
DIY #AI: Running Powerful Models Locally to Save Money and Protect Privacy
Break free from subscription based AI! In this hands on workshop, educators will install and configure Ollama, Page Assist to run powerful AI models directly on their devices. Yo
Exploring OpenThinker:7b #ollama #GenAI #AI
While much of my experiments on the desktop with GenAI have been disappointing (Gemma3:latest is one model that works well after a pause), I have found that models like tinyllama,
AI Privacy for Various Scenarios #AI #EdTech #GoogleGemini
Working on a presentation, I wanted to share these levels of safety from a question I asked Google Gemini. This is research, so if you know better, feel free to drop a comment. I'v
Create Your GenAI Assistant: #Ollama and #PageAssist
Creating custom GPTs, or Boodlebox Bots, Perplexity Spaces, Google Gemini GEMS, Claude Projects is a lot of fun. In this short walkthrough, I’ll share tips for crafting a Bot using
Finding a GUI for Local #AI #Ollama
In a not so surprising twist, I decided to drop other GUI platforms for interacting with local AI solutions. Two things became clear: I needed to optimize for speed and complicated
Local AI Model Comparison (Updated)
I tested several local AI models and mapped my thoughts in this chart. It may not be definitive, but it reflects my experience. Msty is my 2 choice. Ollama