google/gemma-3-4b-it-qat-int4-unquantized

The google/gemma-3-4b-it-qat-int4-unquantized model is a 4.3 billion parameter instruction-tuned variant from the Gemma 3 family, developed by Google DeepMind. This multimodal model handles both text and image inputs, generating text outputs, and features a 128K token context window. It is specifically designed with Quantization Aware Training (QAT) to maintain quality while significantly reducing memory requirements for deployment in resource-limited environments.