mudler/depth-anything.cpp-gguf
Not comparable yet vs depth-anything/DA3-BASE. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (8 of 437/279 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs depth-anything/DA3-BASE. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (8 of 437/279 match), usually an architecture llama.cpp's name map doesn't cover yet.