mradermacher/Phil-18B-il1-i1-GGUF
Quantization vs altomek/Phil-18B-il1. mradermacher/Phil-18B-il1-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 101 tensors match exactly and 202 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/101, MLP 0/100, Attention 0/100