lmstudio-community/datagemma-rig-27b-it-GGUF
Quantization vs google/datagemma-rig-27b-it. lmstudio-community/datagemma-rig-27b-it-GGUF is a GGUF quantization (Q8_0) of the same weights: 185 tensors match exactly and 323 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/185, MLP 0/138, Attention 0/184