mradermacher/ablation-model-c4-i1-GGUF
Quantization vs HuggingFaceFW/ablation-model-c4. mradermacher/ablation-model-c4-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 49 tensors match exactly and 169 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96