Ask HN: How do you use local LLMs?

What applications(as in use cases, not in software names) have you found for local LLMs that you use yourself on a daily basis, and which LLMs do you use?

4 points | by Haeuserschlucht 23 hours ago

1 comments

  • henry_flower 23 hours ago
    not exactly daily, but I use llama3.2-vision (via ollama) to generate a .txt file alongside every photo I take, containing a description of the photo. then I can just grep for, say, "selfie":

        $ alias omglol='find -name \*txt | xargs -n50 grep -li'
        $ omglol selfie
        ./10/IMG_20241019_204444.txt
        ./09/IMG_20240930_082108.txt
        ./09/IMG_20240930_082118.txt
        ./07/IMG_20240712_154559.txt
        ./07/IMG_20240712_154554.txt
    
    or to do a slide show:

        $ omglol selfie | sed s/txt/jpg/ | xargs feh
    • pizza 3 hours ago
      You might be able to load up all the txt files into the embedded vector db in `llm` so that you could also query them semantically.
    • Haeuserschlucht 17 hours ago
      Great idea!