startlux-models/StartLux-Decision-4B-Q8_0-GGUF
Quantization vs startlux-models/StartLux-Decision-4B. startlux-models/StartLux-Decision-4B-Q8_0-GGUF is a GGUF quantization (Q8_0) of the same weights: 81 tensors match exactly and 129 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32