Alibaba Group Holding has introduced a new multimodal artificial intelligence (AI) model capable of processing text, images, audio and video on smartphones and laptops. The company launched Qwen2.5-Omni-7B as the latest addition to its Qwen family of models. With just 7 billion parameters, it is designed to run on mobile phones, tablets and laptops, making advanced AI capabilities more accessible to everyday users. The model can handle various types of inputs and generate real-time responses as text or audio, Alibaba said in a statement. The company made the model open-source, and it is currently available on Hugging Face, Microsoft’s GitHub, and Alibaba’s ModelScope. It is also integrated into the company’s Qwen Chat.
The company highlighted potential uses such as assisting visually impaired users with real-time audio descriptions and providing step-by-step cooking guidance by analyzing ingredients. The model’s versatility underscores the growing demand for AI systems that go beyond text generation. Alibaba’s foundational Qwen models have emerged as popular options for AI developers to build upon, making it one of the few major alternatives to DeepSeek’s V3 and R1 models in mainland China. Qwen2.5-Omni-7B has demonstrated strong performance in benchmark tests. It scored 56.1 on OmniBench, surpassing the 42.9 achieved by Google’s Gemini-1.5-Pro. It also outperformed Alibaba’s earlier Qwen2-Audio model in the CV15 audio benchmark, scoring one point higher with 92.4. For image-related tasks, it achieved 59.2 on the Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark, beating the Qwen2.5-VL vision-language model.
The new model is optimized for portability and efficiency, as larger AI models typically require significant storage and computational power. It is part of a trend towards more efficient models that can be run locally on user machines without the need for an internet connection, addressing data privacy concerns. Alibaba is also joining a global trend towards multimodal models that can handle much more than just text input and output. ChatGPT developer OpenAI made headlines again last week by adding image generation capabilities to its GPT-4o model. TikTok owner ByteDance recently unveiled InfiniteYou, a tool that can re-craft images while preserving subjects’ identities. In January, DeepSeek released Janus-Pro, an updated version of its multimodal model launched in October, the South China Morning Post reports.
