mradermacher/Llama3.1-elm-turbo-6B-instruct-i1-GGUF
Quantization vs slicexai/Llama3.1-elm-turbo-6B-instruct. mradermacher/Llama3.1-elm-turbo-6B-instruct-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 49 tensors match exactly and 170 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96, lm_head 0/1