QuantStack/Wan2.1_T2V_14B_FusionX_VACE-GGUF

Same weights, converted vs QuantStack/Wan2.1_T2V_14B_FusionX_VACE. Same weights stored in another dtype (F16/BF16 → F16/BF16).

Tensors changed: Embeddings 0/12, other 0/71, Attention 0/768, Norms 0/288, MLP 0/192

On the Hub · Downloads on Model Pulse