mradermacher/Melinoe-GLM-30B-A3B-Thinking-GGUF
Quantization vs bgg1996/Melinoe-GLM-30B-A3B-Thinking. mradermacher/Melinoe-GLM-30B-A3B-Thinking-GGUF is a GGUF quantization (Q8_0) of the same weights: 235 tensors match exactly and 331 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/189, MLP 0/187, Attention 0/188