mradermacher/Phi-4-reasoning-Line-14b-karcher-i1-GGUF
Quantization vs mergekit-community/Phi-4-reasoning-Line-14b-karcher. mradermacher/Phi-4-reasoning-Line-14b-karcher-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 81 tensors match exactly and 162 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/80, Attention 0/80