QuantStack/Wan2.2-Fun-5B-Control-GGUF

Quantization vs alibaba-pai/Wan2.2-Fun-5B-Control. QuantStack/Wan2.2-Fun-5B-Control-GGUF is a GGUF quantization (Q8_0) of the same weights: 527 tensors match exactly and 300 within quantization error.

Tensors changed: Attention 0/480, Norms 0/180, MLP 0/120, other 0/37, Embeddings 0/10

On the Hub · Downloads on Model Pulse