mradermacher/pythia-12b-i1-GGUF
Quantization vs EleutherAI/pythia-12b. mradermacher/pythia-12b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 254 tensors match exactly and 110 within quantization error.
Tensors changed: Embeddings 0/2, Attention 0/72, Norms 0/146, MLP 0/144