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:
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:
Is there some sort of calculator to help one determine the best model to run?
LM Studio will let you know what models you can run on your hardware and has a browser that can point you at the most popular models. It only supports Nvidia cards though. Use Kobol.cpp’s nocuda releases if you have an AMD card.
Asking chatgpt Claude or any other llm usually is a good starting point