mradermacher/bloomz-7b1-p3-i1-GGUF
Quantization vs bigscience/bloomz-7b1-p3. mradermacher/bloomz-7b1-p3-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 214 tensors match exactly and 91 within quantization error.
Tensors changed: Norms 0/122, MLP 0/120, Attention 0/60, Embeddings 0/3