mradermacher/Hermetic-Llama-Ties-GGUF
Quantization vs JoPmt/Hermetic-Llama-Ties. mradermacher/Hermetic-Llama-Ties-GGUF is a GGUF quantization (Q8_0) of the same weights: 21 tensors match exactly and 72 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/21, MLP 0/30, Attention 0/40