from Hacker News

Ask HN: People with new Macs / computers with GPU's, do you run LLM's locally?

by vishalontheline on 5/9/25, 4:42 AM with 2 comments

I am considering finally upgrading to a new computer - most likely an M4 Mac with the primary goal of running coding assistants and training my own models locally.

Is this a good idea? Have you tried it? How's the performance?

Thank you!

  • by fiiv on 5/9/25, 5:10 AM

    I do this. Ollama makes it very easy - just pull the model you want. The great thing is the ability to test them in the same tasks, there's a huge difference in comparable models.

    You can set it up in your editor of choice - I use Zed, and it's just listed as one of the providers you can choose.

    In terms of performance - it works decently well.

  • by bookworm123 on 5/9/25, 6:29 AM

    Cool idea, however when I have to create an account for a service just to test it out, I will naturally decline to do so. Maybe you could upload a sample document for people to play with?