mradermacher/gptailor-llama3-8b-i1-GGUF
Quantization vs guinansu/gptailor-llama3-8b. mradermacher/gptailor-llama3-8b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 47 tensors match exactly and 163 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/47, MLP 0/69, Attention 0/92