mradermacher/RYS-Phi-3-medium-4k-instruct-GGUF
Quantization vs dnhkng/RYS-Phi-3-medium-4k-instruct. mradermacher/RYS-Phi-3-medium-4k-instruct-GGUF is a GGUF quantization (Q8_0) of the same weights: 103 tensors match exactly and 206 within quantization error.
Tensors changed: Norms 0/103, MLP 0/102, Attention 0/102, lm_head 0/1, Embeddings 0/1