I’ve been looking into self-hosting LLMs or stable diffusion models using something like LocalAI and / or Ollama and LibreChat.

Some questions to get a nice discussion going:

  • Any of you have experience with this?
  • What are your motivations?
  • What are you using in terms of hardware?
  • Considerations regarding energy efficiency and associated costs?
  • What about renting a GPU? Privacy implications?
  • Possibly linux@lemmy.zip
    link
    fedilink
    English
    arrow-up
    1
    ·
    5 months ago

    I run ollama on my laptop in a VM with open web UI. It works great and I have plenty of models to choose from.

    I recently was playing around with TTS and it is pretty solid as well. I am thinking about taking the smaller phi models and throwing it onto my pine64 quartz64 for a portable AI assistant while traveling. The only potential problem is the time it takes to process.