stduhpf/dreamshaper-8LCM-im-GGUF-sdcpp
LoRA-style vs Lykon/dreamshaper-8-lcm. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of out_proj, q_proj, v_proj changed, in 3 of 12 layers; norms, biases and embeddings are untouched.
Tensors changed: other 0/523, Embeddings 0/6, Norms 0/282, MLP 0/48, Attention 3/272