Ollama is an open-source project that serves as a powerful and user-friendly platform for running LLMs on your local machine.
Discussion
I started using Ollama 2 days ago. Pretty easy to get up and running.
A little disappointed though at the size of the models I can run at a useful speed.
405b is completely out of my grasp.
I don't think I could run this on my machine. It's so laggy with LM Studio, I had to give up.
Pretty happy with Venice.ai since they enabled 405B.