Anyone got a good deepseek R1 local rig build? I hope to get a YouTube video link

[ubergarm]

While I don’t have a YT video link, we do have a thread about running R1 locally over here:

DeepSeek R1 671B backed by fast read IOPS?

Yeah the landscape of inference engines and models is overwhelming. I’ve tried many of them out locally and in general llama.cpp is the upstream source for many of the other projects. It also has some of the best capability for doing partial offload between GPU/RAM and most importantly for this test is it supports mmap() letting the big model file…

---

An early build was described in this post:

Thread by @carrigmat on Thread Reader App