Novice25/FireRed-Image-Edit-1.1_GGUF
Quantization vs cocorang/FireRed-Image-Edit-1.1-FP8_And_BF16. Novice25/FireRed-Image-Edit-1.1_GGUF is a GGUF quantization (Q8_0) of the same weights: 1093 tensors match exactly and 840 within quantization error.
Tensors changed: other 0/246, Norms 0/243, Embeddings 0/4, Attention 0/960, MLP 0/480