KittyLM/kittylm-gemma3-1b-gguf
Quantization vs KittyLM/kittylm-gemma3-1b. KittyLM/kittylm-gemma3-1b-gguf is a GGUF quantization (Q8_0) of the same weights: 157 tensors match exactly and 183 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/157, MLP 0/78, Attention 0/104