Do you host your own ML / AI / LLM? What do you use, and what do you use it for?

  • Steve@startrek.website
    link
    fedilink
    English
    arrow-up
    1
    ·
    17 days ago

    I recently gave it a try with qwen3.5 and deepseek coder v2. I have a RTX3090 and these are the largest models that can run comfortably on it.

    Conclusion, they are both fucking useless. Free tier claude runs circles.