mradermacher/Llama-3.1-5B-Instruct-18Layers-GGUF
Quantization vs kechengcode/Llama-3.1-5B-Instruct-18Layers. mradermacher/Llama-3.1-5B-Instruct-18Layers-GGUF is a GGUF quantization (Q8_0) of the same weights: 37 tensors match exactly and 128 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/37, MLP 0/54, Attention 0/72