mradermacher/ERNIE-4.5-29B-A4B-PT-i1-GGUF
Quantization vs win10/ERNIE-4.5-29B-A4B-PT. mradermacher/ERNIE-4.5-29B-A4B-PT-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 111 tensors match exactly and 260 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/75, MLP 0/147, Attention 0/148