Green-Sky/flux.1-lite-8B-GGUF
LoRA-style vs Freepik/flux.1-lite-8B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of 2 changed, in 0 of 0 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/108, Attention 0/64, MLP 1/64, other 0/280