Lythri/Lythri-7B-A4B-Q4_0_8-GGUF
Quantization vs Lythri/Lythri-7B-A4B. Lythri/Lythri-7B-A4B-Q4_0_8-GGUF is a GGUF quantization (Q4_0_8) of the same weights: 279 tensors match exactly and 344 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/278, MLP 0/126, other 0/85, Attention 0/132