1. Download / Install / Run pull ollama

01 - Download / Install

Checkout Mikey Vibe Coding and or tech with tim LLM Local

for installation instructions

02 - Provides a list

check out mikes tutorial for install, after, run ollama to check

He uses

Llama3

8B parameters, 4.7GB

you need:

  • 8GB of Ram to run 7B Models,
  • 16GB to run 13B
  • 32GB for 33B

03 - Run With pyhon

Pick a model to use https://ollama.com/library

run

ollama run llama3

You can pull to download a mode, but i believe in you run a model, it will auto download / install

when running ollama in terminal use /bye to quit/exit

/bye