mradermacher/pythia-6.9b-HC3-i1-GGUF
Quantization vs pszemraj/pythia-6.9b-HC3. mradermacher/pythia-6.9b-HC3-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 226 tensors match exactly and 98 within quantization error.
Tensors changed: Embeddings 0/2, Attention 0/64, Norms 0/130, MLP 0/128