QuantStack/Wan2.2-S2V-14B-GGUF
Quantization vs Wan-AI/Wan2.2-S2V-14B. QuantStack/Wan2.2-S2V-14B-GGUF is a GGUF quantization (Q8_0) of the same weights: 860 tensors match exactly and 400 within quantization error.
Tensors changed: Attention 0/640, Norms 0/264, MLP 0/160, other 0/186, Embeddings 0/10