This quant collection
REQUIRES ik_llama.cpp fork to support advanced non-linear SotA quants. Do
not download these big files and expect them to run on mainline vanilla llama.cpp, ollama, LM Studio, KoboldCpp, etc!
These quants provide best in class quality for the given memory footprint.
Shout out to
@ubergarm for his diligent work on ik_llama.cpp oriented quanting.
