mudler/locate-anything.cpp-gguf
Not comparable yet vs nvidia/LocateAnything-3B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (6 of 770/770 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs nvidia/LocateAnything-3B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (6 of 770/770 match), usually an architecture llama.cpp's name map doesn't cover yet.