mradermacher/bloomz-1b7-i1-GGUF
Quantization vs bigscience/bloomz-1b7. mradermacher/bloomz-1b7-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 172 tensors match exactly and 73 within quantization error.
Tensors changed: Norms 0/98, MLP 0/96, Attention 0/48, Embeddings 0/3