7.9B total. 1.3B active. One DGX Spark. No cluster. Ling-3.0-tiny × ASystem AReno closes the Agentic RL post-training loop-locally, on a single DGX Spark. Running locally is only step one. Ling-3.0-tiny makes iteration practical; ASystem AReno turns task feedback into a trainable, retestable loop on one node.
AI 导读
总参数量 7.9B，激活参数 1.3B。一台 DGX Spark，无需集群。Ling-3.0-tiny × ASystem AReno 在单台 DGX Spark 上本地闭环完成智能体强化学习后训练。本地运行只是第一步。Ling-3.0-tiny 让迭代变得切实可行；ASystem AReno 将任务反馈转化为单节点上可训练、可重测的闭环。
7.9B total. 1.3B active. One DGX Spark. No cluster. Ling-3.0-tiny × ASystem AReno closes the Agentic RL post-training loop-locally, on a single DGX Spark. Running locally is only step one. Ling-3.0-tiny makes iteration practical; ASystem AReno turns task feedback into a trainable, retestable loop on one node.
来源：Ant Ling· x.com