本地AI栈：DeepSeek v4 flash与GLM 5.2分工跑在DGX上
@MiaAI_lab https://t.co/zJU4GuHSVq
本地AI栈：DGX Sparks跑DeepSeek v4，Stations跑GLM 5.2，Brev编排。
Alec Fong公开其本地AI配置：2台DGX Sparks运行DeepSeek v4 flash，推理速度90 tok/sec，负责执行与子智能体。
另2台DGX Stations运行GLM 5.2 nvfp4，速度120 tok/sec，负责规划与顾问。
整个集群用Brev做网络连接、常驻云智能体和编排。
@MiaAI_lab https://t.co/zJU4GuHSVq
@MiaAI_lab x.com/alecqfong/stat… Alec Fong @alecqfong Current local ai stack 2x DGX Sparks - DeepSeek v4 flash (90 tok/sec) - implementation & sub agents 2x DGX Stations - GLM 5.2 nvfp4 (120 tok/sec) - planning and advising Brev for cluster networking, always on cloud agent, and orchestration 🔗 View Quoted Tweet
This report is categorized under AITOP's "How-to" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include DeepSeek v4, GLM 5.2, DGX Sparks, DGX Stations.
Source attribution: curated from NVIDIA AI (@NVIDIAAI).
