mradermacher/phi-4-45b-i1-GGUF
Quantization vs ehristoforu/phi-4-45b. mradermacher/phi-4-45b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 261 tensors match exactly and 522 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/261, MLP 0/260, Attention 0/260