Lorelum/granite-embedding-97m-multilingual-r2-GGUF
Quantization vs ibm-granite/granite-embedding-97m-multilingual-r2. Lorelum/granite-embedding-97m-multilingual-r2-GGUF is a GGUF quantization (Q4_0) of the same weights: 25 tensors match exactly and 49 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/24, Attention 0/24, MLP 0/24