• AmbiguousProps
      link
      fedilink
      English
      235 days ago

      That’s fair, but I think I’d rather self host an Ollama server and connect to it with an Android client in that case. Much better performance.

      • @OhVenus_Baby@lemmy.ml
        link
        fedilink
        English
        24 days ago

        How is Ollama compared to GPT models? I used the paid tier for work and I’m curious how this stacks up.

        • AmbiguousProps
          link
          fedilink
          English
          14 days ago

          It’s decent, with the deepseek model anyway. It’s not as fast and has a lower parameter count though. You might just need to try it and see if it fits your needs or not.

      • Greg Clarke
        link
        fedilink
        English
        45 days ago

        Yes, that’s my setup. But this will be useful for cases where internet connection is not reliable

      • Greg Clarke
        link
        fedilink
        English
        35 days ago

        Has this actually been done? If so, I assume it would only be able to use the CPU

        • @Euphoma@lemmy.ml
          link
          fedilink
          English
          74 days ago

          Yeah I have it in termux. Ollama is in the package repos for termux. The speed it generates does feel like cpu speed but idk