I have experience in running servers, but I would like to know if it’s possible to do it, I just need a GPT 3.5 like private LLM running.

  • MasterNerd@lemm.eeEnglish
    0·
    5 months ago

    Look into ollama. It shouldn’t be an issue if you stick to 7b parameter models

    • TheBigBrother@lemmy.worldOPEnglish
      0·
      5 months ago

      Yeah, I did see something related to what you mentioned and I was quite interested. What about quantized models?

      • entropicdrift@lemmy.sdf.orgEnglish
        0·
        5 months ago

        Quantized with more parameters is generally better than floating point with fewer parameters. If you can squeeze a 14b parameter model down to a 4-bit int quantization it’ll still generally outperform a 16-bit Floating Point 7b parameter equivalent.