Ant Group and Tsinghua Open-Source 9B Model Realtime-Venus for Async Parallel AI Task Execution
What happened
蚂蚁集团和清华开源了一个9B参数模型Realtime-Venus，核心是一套叫Harness的框架，把用户对话和后台执行拆开。以前AI办事得一句一问等回复，现在模型可以一边跟用户聊天，一边异步去查资料、填表单，多个任务同时跑。9B的参数量不算大，适合资源有限的部署场景。正文没披露训练数据、跑分和部署成本，实际效果和性价比还得自己测。
Coverage
Follow the reports to see the story from different sides.
- QbitAI · WeChatAnt Group and Tsinghua Open-Source 9B Model Realtime-Venus for Async Parallel AI Task Execution
Ant Group and Tsinghua University open-sourced the 9B-parameter model Realtime-Venus, featuring a Harness framework that decouples front-end dialogue from back-end execution. It enables the model to handle multiple tasks in parallel—chatting with users while asynchronously performing operations like data retrieval or form filling. This addresses the inefficiency of turn-by-turn AI interaction. The 9B size suits resource-constrained deployments. The post does not disclose training data, benchmark scores, or deployment costs.