deepseek-ai/DeepSeek-V4-Pro-0813 · Hugging Face
huggingface.co
We’re on a journey to advance and democratize artificial intelligence through open source and open science.

This is an MoE model with 1.6T-A49B

The weights were up briefly then taken down due to some issues in the repo files apparently, now they’re back up:

GGUFs are out as well:

DeepSeek published benchmarks for reference:

  • Jo Miran@lemmy.mlEnglish
    1·
    3 days ago

    Is there some sort of calculator to help one determine the best model to run?

      • Jo Miran@lemmy.mlEnglish
        2·
        3 days ago

        I’m actually curious as to what’s the most I can run on an Apple M4 Max system.

            • lynx@sh.itjust.worksEnglish
              2·
              19 hours ago

              With Q4 everything below 150B should be fine. You can also run the -Flash variant of this model in Q1, but it is probably not usable.

            • e0qdk@reddthat.comEnglish
              2·
              3 days ago

              If I understand the nature of your hardware correctly, you should be able to run the MoE models like Gemma4 26B-A4B or Qwen3.6 35B-A3B at a high quantization fairly performantly.

              You could try running some of the dense models (like today’s Qwen 3.8 27B) as well, but I expect they’ll be pretty slow (judging by my own experience with a unified RAM system that has a Strix Halo APU). Might still be useful for tasks that you can leave running on their own for a long time instead of for interactive chat style interaction though.

              You’ve got enough RAM to load larger models, but there hasn’t been much released in between the “it fits on a 24GB or 32GB GPU that a gamer might own” and the “oh god you need HOW MUCH RAM!?” scales lately…