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:

  • SirDimples@programming.devOPEnglish
    7·
    17 days ago

    free to use if you have the hardware. For this model because of its size, the main problem is the hardware availability/cost. But in general there are 3 ways to run an open weights model:

    • pay a provider like DeepSeek/OpenRouter per usage
    • buy hardware that can run it locally: actually not a bad investment for a business
    • rent hardware that can run it from a cloud provider, hardware can be rented dedicated or time-shared (so called serverless).
    • Jo Miran@lemmy.mlEnglish
      1·
      16 days ago

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

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

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

              • SirDimples@programming.devOPEnglish
                1·
                6 days ago

                You might want to try running Ling-3.0-Flash (124B-A5.1B) it might be perfect for your M4 and should perform close to the level of DeepSeek V4 Flash preview or MiniMax M2.7

              • lynx@sh.itjust.worksEnglish
                2·
                14 days 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·
                16 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…