google/gemma-3-12b-it-qat-q4_0-unquantized

The google/gemma-3-12b-it-qat-q4_0-unquantized model is a 12 billion parameter instruction-tuned multimodal language model from Google DeepMind's Gemma 3 family. It handles both text and image inputs, generating text outputs, and features a 32K token context window. This specific version utilizes Quantization Aware Training (QAT) to maintain quality while enabling efficient quantization to Q4_0, making it suitable for resource-constrained environments.