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:
DeepSeek V4 Pro 0813 Weights Released!
https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813
9 Comments
nieceandtows@programming.dev · 2 pts · 4d
Are these free to use, or do you have to pay?
SirDimples@programming.dev · 7 pts · 4d
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:
JoMiran@lemmy.ml · 1 pts · 4d
Is there some sort of calculator to help one determine the best model to run?
Even_Adder@lemmy.dbzer0.com · 2 pts · 4d
JoMiran@lemmy.ml · 2 pts · 3d
I'm actually curious as to what's the most I can run on an Apple M4 Max system.
e0qdk@reddthat.com · 1 pts · 3d
How much RAM do you have?
JoMiran@lemmy.ml · 2 pts · 3d
96gb
e0qdk@reddthat.com · 2 pts · 3d
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...
lynx@sh.itjust.works · 2 pts · 2d
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.
Shimitar@downonthestreet.eu · 1 pts · 4d
Asking chatgpt Claude or any other llm usually is a good starting point