mradermacher/gpt2-xl-i1-GGUF
Quantization vs openai-community/gpt2-xl. mradermacher/gpt2-xl-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 387 tensors match exactly and 1 within quantization error.
Tensors changed: Attention 0/96, Norms 0/194, MLP 0/96, Embeddings 0/2