manuojvv/Qwen3.5-4B-gabliterated-Q8
Quantization vs jwest33/qwen3.5-4b-gabliterated. manuojvv/Qwen3.5-4B-gabliterated-Q8 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