Fara-7B: An Efficient Agentic Model for Computer Use Published November 24, 2025
Pushing the frontiers of computer-use agents with an open-weight, ultra-compact model, optimized for real-world web tasks


Fara-7B is Microsoft's first agentic small language model (SLM) designed specifically for computer use. With only 7 billion parameters, Fara-7B is an ultra-compact Computer Use Agent (CUA) that achieves state-of-the-art performance within its size class and is competitive with larger, more resource-intensive agentic systems.
微软研究院悄然推进了设备端人工智能的一个里程碑:Fara-7B,一个拥有 70 亿参数的智能小型语言模型 (SLM),旨在通过预测鼠标和键盘操作来查看网页和操作电脑,现在它已作为开源研究成果提供,供用户进行实践实验。
Fara-7B是微软开源发布的70亿参数规模的计算机操作代理(CUA)模型,基于Qwen2.5-VL-7B架构。通过视觉解析网页截图,在屏幕上执行点击、输入等操作,无需依赖额外的可访问性树或多个大模型协作,可直接在Windows 11本地运行,支持NPU加速,实现更低延迟和更好的隐私保护。Fara-7B在WebVoyager、Online-Mind2Web等公开基准测试中表现优异,任务成功率高,部分任务领先同级模型。采用全新的合成数据生成流程进行训练,包含大量任务轨迹和辅助任务数据,以监督微调为主。