英伟达正式支持八节点 DGX Spark 集群，统一内存达 1 TB
英伟达在 GTC 柏林宣布正式支持八节点 DGX Spark 集群，据其技术博客，单节点统一内存为 128 GB，四节点达 512 GB，八节点达 1 TB。英伟达称该容量可让 Z.ai 的完整 GLM 5.3（753B）检查点在 8×128 GB 集群上运行，并用 GLM 5.3 Flash 实测生成速度约 80 tokens/s。厂商基准还显示，稠密 Qwen3.8-27B 的解码速度从单节点约 12 TPS 提升到八节点 52 TPS，nanochat 预训练取得 7.79 倍加速、97.4% 扩展效率；英伟达表示 NVIDIA Sync 的八节点支持（其 Cluster Assistant 负责配置与设备管理）将在年底前推出。
这些数据来自英伟达单篇博客的厂商说法，但显示桌面级 Spark 集群可在本地服务大型开放模型并训练小模型。
AI developers aren’t just running a single model anymore—they’re orchestrating multiple models in parallel, chaining inference calls, and experimenting with frontier-class architectures that demand hundreds of gigabytes of memory. NVIDIA DGX Spark was built to bring AI development to the desk, and now you’ll be able to link even more Spark nodes together.
At GTC Berlin, NVIDIA announced official support for eight-node DGX Spark clusters, scaling unified memory to 1 TB and opening the door to frontier-class models, multi-agent workloads, and near-linear pre-training—all running locally.
NVIDIA Sync makes it easy to cluster. Its Cluster Assistant handles setup and device management. Support for eight-node clusters in NVIDIA Sync is coming by the end of the year.
Read on for benchmark data on how inference, orchestration, and training scale as the cluster grows.
Run larger, newer frontier-class models
The biggest benefit of an eight-node cluster is memory. A single DGX Spark provides 128 GB of unified memory; four nodes reach 512 GB; eight nodes reach 1 TB. That capacity opens the door to a class of models that previously wouldn’t start on a four-node system, including the full GLM 5.3 (753B) model from Z.ai.
#NVIDIA#DGX Spark#NVIDIA Sync#GLM 5.3#Z.ai#Qwen3.8-27B#nanochat#MiniCPM