mradermacher/Gemma-merged-2B-ties-i1-GGUF
Quantization vs arcee-ai/Gemma-merged-2B-ties. mradermacher/Gemma-merged-2B-ties-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 37 tensors match exactly and 127 within quantization error.
Tensors changed: Norms 0/37, MLP 0/54, Attention 0/72, Embeddings 0/1