Event ·Multi-source

DGX Spark本地跑模型指南:DeepSeek v4 Flash与GLM-5.2搭配

NVIDIA AI官方转发了一份来自MiaAI_lab的DGX Spark本地模型运行指南。1台DGX Spark可跑DeepSeek v4 Flash(1M上下文,26 tok/s)或Qwen 3.6 35b NVFP4(256k上下文,81 tok/s)。2台DGX Spark是性价比甜点,DeepSeek v4 Flash速度提升到82 tok/s,还能跑Inkling-Small等全模态模型。3台以上可跑GLM-5.2 with Vision,348k上下文、25 tok/s,被称为本地最强智能。指南还给出了4台时的多卡分工方案,比如2台跑DeepSeek v4 Flash,另外2台跑图像模型和ComfyUI。

Current read

本地跑大模型?这份DGX Spark指南从1台到4台,告诉你选哪款模型、速度多少。

9 sources58° AI heatLast updated 2026/8/5 19:35:09

Evidence

9 sources
Related source 2AI Engineer
View source
Related source 4arXiv: DeepSeek
View source
Related source 8歸藏(guizang.ai)
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.