• surewhynotlem@lemmy.world
    link
    fedilink
    arrow-up
    2
    ·
    21 hours ago

    How’s the local LLM support on Linux with AMD?

    (Yes I could google, but I think people here would give more realistic answers at a more reasonable tech skill level)

    • ozymandias117@lemmy.world
      link
      fedilink
      English
      arrow-up
      4
      ·
      edit-2
      18 hours ago

      llama.cpp (and by extension Ollama) has a Vulkan backend now, which works fine for my usecases on AMD