ngquocvinh/Spark-X2.5-1.7B-GGUF
Quantization vs XHToken/Spark-X2.5-1.7B. ngquocvinh/Spark-X2.5-1.7B-GGUF is a GGUF quantization (Q8_0) of the same weights: 57 tensors match exactly and 141 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/56