mradermacher/Qwen3-30B-A3B-Thinking-2507-Amoral-Edition-GGUF
Quantization vs rodrigomt/Qwen3-30B-A3B-Thinking-2507-Amoral-Edition. mradermacher/Qwen3-30B-A3B-Thinking-2507-Amoral-Edition-GGUF is a GGUF quantization (Q8_0) of the same weights: 241 tensors match exactly and 194 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/193, MLP 0/48, Attention 0/192