soichisumi/multilingual-e5-large-Q8_0-GGUF
Quantization vs intfloat/multilingual-e5-large. soichisumi/multilingual-e5-large-Q8_0-GGUF is a GGUF quantization (Q8_0) of the same weights: 242 tensors match exactly and 145 within quantization error.
Tensors changed: Embeddings 0/3, Norms 0/96, Attention 0/192, other 0/96