aiXcoder open-sources 4B context compression model for coding agents
aiXcoder has open-sourced aiXcompact-4B, a 4B-parameter model that compresses coding-agent histories by retaining key requirements, condensing tool results, removing stale records and producing structured task summaries. The model supports private deployment on a single A100-40GB GPU. aiXcoder claims that, when connected to OpenCode, it matched DeepSeek-V4-Pro’s overall task-completion accuracy on Terminal-Bench, while cutting private-deployment inference costs by 78% for specified tasks; these benchmark and cost figures have not been independently verified.
The release offers a specialized, locally deployable option for controlling token usage in long-running coding-agent workflows, though its reported quality and savings remain vendor claims.

智东西 作者 | 杨京丽 编辑 | 李水青
智东西11月11日报道,今日,孵化自北京大学软件工程研究所的AI编程创企硅心科技(aiXcoder)开源上下文压缩专用模型aiXcompact-4B。该模型主要面向编程Agent的长程复杂研发任务场景,参数量仅4B,支持单张A100-40GB显卡私有化部署。
aiXcompact-4B进行上下文压缩时,能够针对编程Agent的历史轨迹进行结构化处理:保留关键原始信息,精简文件读取、代码搜索和测试运行等工具返回结果,删除重复或失去参考价值的中间记录,并生成结构化任务摘要,以较低成本减少后续重复输入带来的Token开销。
根据aiXcoder公布的数据,在Terminal-Bench基准测试中,将aiXcompact-4B接入OpenCode进行上下文压缩测试后,整体任务完成准确率与DeepSeek-V4-Pro持平。在私有化部署场景下,针对特定任务的单次GPU推理成本较DeepSeek-V4-Pro降低78%。
#aiXcoder#aiXcompact-4B#OpenCode#DeepSeek-V4-Pro#Terminal-Bench#NVIDIA A100