mradermacher/Phi-4-mini-UNOFFICAL-GGUF

Same weights, converted vs Xiaojian9992024/Phi-4-mini-UNOFFICAL. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/17, MLP 0/16, Attention 0/16

On the Hub · Downloads on Model Pulse