Felladrin/gguf-sharded-Phi-3-mini-4k-instruct
Quantization vs microsoft/Phi-3-mini-4k-instruct. Felladrin/gguf-sharded-Phi-3-mini-4k-instruct is a GGUF quantization (Q8_0/F16) of the same weights: 67 tensors match exactly and 128 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/64, Attention 0/64, lm_head 0/1