• Womble@piefed.world
      link
      fedilink
      English
      arrow-up
      3
      arrow-down
      10
      ·
      10 days ago

      You almost certainly weren’t using a Deepseek model offline (unless you have 100s of GB of RAM/VRAM). You might have been using a small model distilled on Deepseek responses, but the smallest model made by Deepseek is about a 300B param model.