• Ptsf@lemmy.world
      link
      fedilink
      arrow-up
      7
      arrow-down
      2
      ·
      8 days ago

      You literally can. Kimi k3 is fist for fist punching at both sol and fable levels. The smaller qwen 3.8 27b is benching well against gpt 5.4 and opus 4.7. There are unreleased internal models you cannot run locally but you also can’t buy them. Additionally, big models are generally bad tools, you’re much better off tuning a local model for your specific task (Wendel from level 1 has a good video on this). If you’re gonna make claims at least do a Google search.

    • -☆-@lemmy.blahaj.zone
      link
      fedilink
      English
      arrow-up
      4
      ·
      8 days ago

      That’s true, but they’re dumbasses. I don’t need Grok, or whatever awful shit facebook made, if I can localhost Qwen

    • Jackinopolis@sh.itjust.works
      link
      fedilink
      arrow-up
      2
      ·
      8 days ago

      There’s also Colibri which runs large models off of a SSD at a much slower speed than corporations. The large high-quality stuff has been gated by big-tech with gigantic GPUs. Colibri, if nothing else than a proof of concept, shows that high quality stuff can run on anything with a hit to speed.