• Chee_Koala@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    edit-2
    13 days ago

    Any 27b Model you can currently recommend for a 16gb AMD ? Mostly coding tasks but not exclusively.

    • deleted@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      12 days ago

      For your hardware, the VRam is not enough to run 27b but, I’d recommend Qwen 3.5 9b for image / text to text.

      And I’m planning to experiment with Qwen 3.8 9b for text to text.

      4_k_m quantization is the sweet spot for performance and ram usage.

      Also, I find Llama cpp is better than Ollama in terms of performance.

    • mierdabird@lemmy.dbzer0.com
      link
      fedilink
      English
      arrow-up
      0
      ·
      13 days ago

      9060xt 16gb is the most cost effective new GPU, but if you’re going used look for a V620 on eBay. It’s a 6800xt chip but in server form factor GPU with 32GB vram. Can be a bit of a pain to set up but by far the most cost effective option IMO

      • Darkaga@lemmy.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        12 days ago

        V620s were a good deal when you could get them for $350, now they’re $700+ and no longer a good deal.