mradermacher/starchat-alpha-GGUF
Quantization vs HuggingFaceH4/starchat-alpha. mradermacher/starchat-alpha-GGUF is a GGUF quantization (Q8_0) of the same weights: 323 tensors match exactly and 161 within quantization error.
Tensors changed: Attention 0/160, Norms 0/162, MLP 0/160, Embeddings 0/2