google/gemma-3-4b-pt

Gemma 3 4.3B-parameter pre-trained model by Google DeepMind is a lightweight, multimodal large language model with a 32768-token context window, capable of handling text and image inputs to generate text outputs. Built from the same research as Gemini models, it supports over 140 languages and excels in text generation, image understanding, question answering, summarization, and reasoning tasks. Its relatively small size allows for deployment in resource-limited environments, democratizing access to advanced AI capabilities.