disham993/electrical-embeddinggemma-ir_q4_k_m
Quantization vs disham993/electrical-embeddinggemma-ir_finetune_16bit. disham993/electrical-embeddinggemma-ir_q4_k_m is a GGUF quantization (Q4_K_M) of the same weights: 145 tensors match exactly and 169 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/72, Attention 0/96