mradermacher/phi-4-25b-GGUF
Quantization vs ehristoforu/phi-4-25b. mradermacher/phi-4-25b-GGUF is a GGUF quantization (Q8_0) of the same weights: 141 tensors match exactly and 282 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/141, MLP 0/140, Attention 0/140