QuantStack/Wan2.2-Fun-5B-InP-GGUF
Quantization vs alibaba-pai/Wan2.2-Fun-5B-InP. QuantStack/Wan2.2-Fun-5B-InP-GGUF is a GGUF quantization (Q8_0) of the same weights: 525 tensors match exactly and 300 within quantization error.
Tensors changed: Attention 0/480, Norms 0/180, MLP 0/120, other 0/35, Embeddings 0/10