shivnathtathe/nvidia_Riva-Translate-4B-Instruct-v2-GGUF
Quantization vs nvidia/Riva-Translate-4B-Instruct-v2. shivnathtathe/nvidia_Riva-Translate-4B-Instruct-v2-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 69 tensors match exactly and 239 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/69, MLP 0/102, Attention 0/136