Based off of deepseek coder, the current SOTA 33B model, allegedly has gpt 3.5 levels of performance, will be excited to test once I’ve made exllamav2 quants and will try to update with my findings as a copilot model

  • noneabove1182@sh.itjust.worksOPM
    link
    fedilink
    English
    arrow-up
    2
    ·
    10 months ago

    The 3060 is a nice cheap one for running okay sized models, but if you can find a way to stretch for a 3090 or a 7900 XTX you’ll be able to run these 33B models with decent quant levels

    • Alex@lemmy.ml
      link
      fedilink
      English
      arrow-up
      3
      ·
      10 months ago

      I was hoping to avoid Nvidia’s binary drivers although I don’t know what the driver/support status of dedicated AI accelerators are like on Linux._