mradermacher/Llama-3_1-Nemotron-51B-Instruct-GGUF
Quantization vs nvidia/Llama-3_1-Nemotron-51B-Instruct. mradermacher/Llama-3_1-Nemotron-51B-Instruct-GGUF is a GGUF quantization (Q6_K) of the same weights: 153 tensors match exactly and 458 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/153, MLP 0/240, Attention 0/216, lm_head 0/1