mradermacher/Llama-3.1-Nemotron-93B-Instruct-HF-early-i1-GGUF
Quantization vs ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-early. mradermacher/Llama-3.1-Nemotron-93B-Instruct-HF-early-i1-GGUF is a GGUF quantization (IQ4_XS) of the same weights: 211 tensors match exactly and 737 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/211, MLP 0/315, Attention 0/420