mradermacher/gpt2-mini-i1-GGUF
Quantization vs erwanf/gpt2-mini. mradermacher/gpt2-mini-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 35 tensors match exactly and 1 within quantization error.
Tensors changed: Attention 0/8, Norms 0/18, MLP 0/8, Embeddings 0/2