aifeifei798/Couture-Engine-31B-v1.0-lora
Adapter vs google/gemma-4-31B-it-qat-q4_0-unquantized. aifeifei798/Couture-Engine-31B-v1.0-lora is a LoRA adapter, not full weights: rank 16, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 60 layers (410 adapted matrices). It modifies google/gemma-4-31B-it-qat-q4_0-unquantized at load time.