I got 32 additional GB of ram at a low, low cost from someone. What can I actually do with it?

  • zkfcfbzr
    link
    English
    225 days ago

    I have 16 GB of RAM and recently tried running local LLM models. Turns out my RAM is a bigger limiting factor than my GPU.

    And, yeah, docker’s always taking up 3-4 GB.

    • Mubelotix
      link
      fedilink
      55 days ago

      Either you use your CPU and RAM, either your GPU and VRAM

      • zkfcfbzr
        link
        English
        25 days ago

        Fair, I didn’t realize that. My GPU is a 1060 6 GB so I won’t be running any significant LLMs on it. This PC is pretty old at this point.

        • @[email protected]
          link
          fedilink
          English
          15 days ago

          You could potentially run some smaller MoE models as they don’t take up too much memory while running. I’d suspect the deepseek r1 8B distill with some quantization would work well.

          • zkfcfbzr
            link
            English
            15 days ago

            I tried out the 8B deepseek and found it pretty underwhelming - the responses were borderline unrelated to the prompts at times. The smallest I had any respectable output with was the 12B model - which I was able to run, at a somewhat usable speed even.