I’ve been following the work that went into this video for a couple of months and have grown to love Level1Techs.
Check out their forum and especially Ubergarm
I’ve been following the work that went into this video for a couple of months and have grown to love Level1Techs.
Check out their forum and especially Ubergarm
Their setup is here:
https://forum.level1techs.com/t/full-deepseek-q1-with-the-ik-version-of-llama-cpp-on-am5-no-distills-just-a-quant/233530
Oh, so an NVIDIA card with 24GB VRAM
Yep, and 2x64gb RAM