Way to run DeepSeek's 671B AI model without expensive GPUs discovered

[Redaktion]

Hugging Face engineer Matthew Carrigan recently revealed on X a method to locally run DeepSeek's advanced R1 model with 8-bit quantization, eliminating the need for expensive GPUs, for a reported cost of $6,000. The key? Having a lot of memory as opposed to vast computing power reserves.

https://www.notebookcheck.net/Way-to-run-DeepSeek-s-671B-AI-model-without-expensive-GPUs-discovered.956421.0.html