liodon-ai/LocateAnything-3B-imatrix-GGUF
Quantization (fewer layers) vs nvidia/LocateAnything-3B. liodon-ai/LocateAnything-3B-imatrix-GGUF matches part of nvidia/LocateAnything-3B (435 of its 770 tensors; the rest of nvidia/LocateAnything-3B has no counterpart). On the shared part: liodon-ai/LocateAnything-3B-imatrix-GGUF is a GGUF quantization (Q8_0) of the same weights: 181 tensors match exactly and 254 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252, lm_head 0/1