mradermacher/ERNIE-4.5-21B-A3B-Thinking-i1-GGUF
Quantization vs baidu/ERNIE-4.5-21B-A3B-Thinking. mradermacher/ERNIE-4.5-21B-A3B-Thinking-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 84 tensors match exactly and 197 within quantization error.
Tensors changed: MLP 0/111, Embeddings 0/1, Norms 0/57, Attention 0/112