lesliemore/z-image-turbo-nsfw-v2-GGUF
Quantization vs tewea/z_image_turbo_bf16_nsfw. lesliemore/z-image-turbo-nsfw-v2-GGUF is a GGUF quantization (Q8_0) of the same weights: 271 tensors match exactly and 180 within quantization error.
Tensors changed: Embeddings 0/9, Norms 0/204, Attention 0/68, MLP 0/102, other 0/68