spiritfather/Gemma4-Gutenberg-26B-A4B-i1-GGUF
Adapter vs nbeerbower/Gemma4-Gutenberg-26B-A4B-lora. nbeerbower/Gemma4-Gutenberg-26B-A4B-lora is a LoRA adapter, not full weights: rank 64, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 30 layers (205 adapted matrices). It modifies spiritfather/Gemma4-Gutenberg-26B-A4B-i1-GGUF at load time.