MaziyarPanahi/phi-4-GGUF

Same weights, converted vs microsoft/phi-4. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/80, Attention 0/80, lm_head 0/1

On the Hub · Downloads on Model Pulse