I’ve tried coding and every one I’ve tried fails unless really, really basic small functions like what you learn as a newbie compared to say 4o mini that can spit out more sensible stuff that works.

I’ve tried explanations and they just regurgitate sentences that can be irrelevant, wrong, or get stuck in a loop.

So. what can I actually use a small LLM for? Which ones? I ask because I have an old laptop and the GPU can’t really handle anything above 4B in a timely manner. 8B is about 1 t/s!

  • entwine413@lemm.eeEnglish
    12·
    16 hours ago

    I’ve integrated mine into Home Assistant, which makes it easier to use their voice commands.

    I haven’t done a ton with it yet besides set it up, though, since I’m still getting proxmox configured on my gaming rig.

    • Passerby6497@lemmy.worldEnglish
      1·
      9 hours ago

      What are you using for voice integration? I really don’t want to buy and assemble their solution if I don’t have to

      • entwine413@lemm.eeEnglish
        1·
        8 hours ago

        I just use the companion app for now. But I am designing a HAL9000 system for my home.