NVIDIA DGX Spark 64GB版发布，支持双机集群扩展
NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI
DGX Spark 提供了极具吸引力的本地 AI 开发方案，特别是双机无损扩容功能解决了单机显存瓶颈，Agent 开发者值得重点关注。
Local AI is becoming more useful by the token.
本地 AI 正以惊人的速度变得愈发实用。
As AI agents move from experiments into everyday development, increasingly capable open models are shrinking to fit on more devices, giving builders more to run locally.
随着 AI 智能体从实验阶段走向日常开发，日益强大的开源模型正不断缩小规模以适应更多设备，为开发者提供了更多可在本地运行的选择。
Coming this month, NVIDIA DGX Spark will be available with 64GB of unified memory from top manufacturer partners — Acer, ASUS, Dell, Gigabyte, HP and MSI — giving developers, researchers and AI enthusiasts a new configuration with DGX OS and the NVIDIA AI software stack ready to use from day one.
本月即将上市，NVIDIA DGX Spark 将配备来自顶级制造商合作伙伴——宏碁、华硕、戴尔、技嘉、惠普和微星——提供的 64GB 统一内存，为开发者、研究人员和 AI 爱好者提供全新配置，预装 DGX OS 和 NVIDIA AI 软件栈，开箱即用。
The new SKU runs capable local agents on device — privately, without cloud dependency. And when workloads grow, two units can cluster together via NVIDIA Sync Cluster Assistant without any additional setup.
这款新 SKU 可在设备上运行功能强大的本地智能体——私密且无需依赖云端。当工作负载增长时，两台设备可通过 NVIDIA Sync Cluster Assistant 进行集群部署，无需任何额外设置。
A New Starting Point for Personal AI Supercomputing
个人 AI 超级计算的新起点
DGX Spark combines NVIDIA Grace Blackwell compute, unified memory, NVIDIA ConnectX-7 networking and an NVIDIA CUDA-accelerated AI software stack in one system. It’s a complete local AI platform for agents, inference, fine-tuning, data science and edge development.
DGX Spark 将 NVIDIA Grace Blackwell 计算能力、统一内存、NVIDIA ConnectX-7 网络以及基于 NVIDIA CUDA 加速的 AI 软件栈整合于一个系统中。它是一个完整的本地 AI 平台，适用于智能体、推理、微调、数据科学和边缘开发。
The compact, personal AI supercomputer provides a place to experiment with models and developers’ own data without turning to a cloud instance for every task.
这款紧凑的个人 AI 超级计算机提供了一个场所，让开发者可以在不依赖云实例的情况下，对模型和自有数据进行实验。
The new 64GB configuration, available exclusively from manufacturer partners, keeps the platform at an accessible price point while retaining the GB10 Grace Blackwell Superchip, DGX OS and full NVIDIA AI software stack — same as the 128GB model. It supports up to 100-billion-parameter models and the agentic applications built on them, fully on device.
这款仅由制造商合作伙伴提供的 64GB 配置在保持可及价格的同时，保留了 GB10 Grace Blackwell 超级芯片、DGX OS 和完整的 NVIDIA AI 软件栈——与 128GB 型号相同。它支持高达千亿参数量的模型及其上构建的智能体应用，全部在设备端运行。
Two 64GB units clustered together don’t just double the memory. In NVIDIA’s Qwen 3.8 27B test, two clustered 64 GB systems delivered up to 1.7x performance compared with a single system, with room to keep scaling as workloads demand.
两台 64GB 设备集群不仅使内存翻倍。在 NVIDIA 的 Qwen 3.8 27B 测试中，两台集群的 64GB 系统相比单台系统性能最高提升了 1.7 倍，并留有根据工作负载需求继续扩展的空间。
DGX Spark ships ready for agent development from day one — NVIDIA Agent Toolkit, CUDA-X AI libraries, Nemotron open models, and popular runtimes like Ollama, vLLM, and PyTorch with CUDA are all supported out of the box. Developers can go from power-on to running models in minutes.
DGX Spark 开箱即支持智能体开发——NVIDIA Agent Toolkit、CUDA-X AI 库、Nemotron 开源模型，以及 Ollama、vLLM 和 PyTorch with CUDA 等流行运行时均得到原生支持。开发者可在几分钟内完成开机并运行模型。
Blender is among the first major creator application providers to support the platform, with a prebuilt, downloadable installer coming soon.
Blender 是首批支持该平台的主要创意应用提供商之一，即将推出预构建的可下载安装程序。
Scale Up With NVIDIA Sync Cluster Assistant
借助 NVIDIA Sync Cluster Assistant 实现扩展
Developers can start with the memory their projects need today and build on a platform designed to seamlessly scale multi-node clusters for larger workloads as their pipelines grow.
开发者可以从项目当前所需的内存起步，在一个旨在无缝扩展多节点集群以应对更大工作负载的平台上构建，随着其管道的增长而扩展。
Every DGX Spark ships with a built-in NVIDIA ConnectX-7 NIC right out of the box. Plus, two units can connect directly with a QSFP cable, pooling their memory to 128GB and expanding model support to up to 200 billion parameters while delivering twice the memory bandwidth and up to 1.7x the performance.
每台 DGX Spark 出厂时均内置 NVIDIA ConnectX-7 网卡。此外，两台设备可通过 QSFP 线缆直接连接，将内存池化至 128GB，并将模型支持扩展至高达 2000 亿参数，同时提供两倍的内存带宽和最高 1.7 倍的性能提升。
The NVIDIA Sync app configures this multi-node cluster seamlessly. The cluster assistant feature detects connected units, validates device configuration and configures the ConnectX-7 network, so developers can focus on their work rather than the infrastructure. Every node runs the same NVIDIA software stack, so nothing needs to be reconfigured when scaling from one unit to two.
NVIDIA Sync 应用可无缝配置此多节点集群。集群助手功能可检测已连接的设备、验证设备配置并设置 ConnectX-7 网络，使开发人员能够专注于工作而非基础设施。每个节点都运行相同的 NVIDIA 软件栈，因此从单台设备扩展到两台设备时无需重新配置任何内容。
And coming at the end of the month, NVIDIA Sync Model Launcher makes running local AI as simple as clicking a few buttons. Developers can download and launch Qwen3.8 27B on a single DGX Spark system or a cluster, with NVIDIA Sync configuring the model to run across connected devices and making it accessible from users’ laptops. The launcher will also set up OpenCode to use the model, so developers can start coding in their browser.
此外，月底即将推出的 NVIDIA Sync Model Launcher 让本地 AI 的运行变得如同点击几个按钮般简单。开发人员可以在单个 DGX Spark 系统或集群上下载并启动 Qwen3.8 27B 模型，由 NVIDIA Sync 配置模型在已连接设备上运行，并从用户的笔记本电脑访问。该启动器还将设置 OpenCode 以使用该模型，使开发人员能够在浏览器中开始编码。
Developer Use Cases on DGX Spark
DGX Spark 上的开发人员用例
The new DGX Spark 64GB configuration supports practical work from day one. With up to 100-billion-parameter models running entirely on device, developers and enthusiasts can start with a single system for models that fit within its memory, or connect multiple DGX Spark systems with NVIDIA Sync Cluster Assistant for workloads that need more memory and compute.
新的 DGX Spark 64GB 配置支持从一开始就开展实际工作。凭借完全在设备上运行的最高 1000 亿参数模型，开发人员和技术爱好者可以从单个系统开始，使用适合其内存容量的模型，或通过 NVIDIA Sync Cluster Assistant 连接多个 DGX Spark 系统，以处理需要更多内存和算力的工作负载。
Here are three workflow examples:
以下是三个工作流程示例：
- Run an AI agent around the clock: Keep a coding or research agent running on DGX Spark, ready to review code, analyze documents or carry out multistep tasks. A cluster provides additional capacity for larger models, longer context windows or multiple agents working at once.
- Power AI apps on your everyday PC: Run a language- or image-generation model on DGX Spark while using an agent or creative application on laptops or desktops. DGX Spark handles the model inference, freeing PCs for other work.
- Scale when the work grows: When a single task outgrows one unit — running a larger model, a longer context window or concurrent agent requests — two DGX Spark 64GB systems connected over the 200 GbE fabric via NVIDIA Sync Cluster Assistant pool their memory to 128GB. The same workflow that ran on one unit scales to two without reconfiguring the software environment.
- 全天候运行 AI 代理：在 DGX Spark 上保持代码或研究代理持续运行，随时准备审查代码、分析文档或执行多步骤任务。集群可为更大模型、更长上下文窗口或多个同时工作的代理提供额外容量。
- 在日常 PC 上为 AI 应用供电：在 DGX Spark 上运行语言或图像生成模型，同时在笔记本电脑或台式机上使用代理或创意应用程序。DGX Spark 负责模型推理，从而释放 PC 用于其他工作。
- 随工作增长而扩展：当单个任务超出单台设备的处理能力——例如运行更大模型、更长上下文窗口或并发代理请求时——通过 NVIDIA Sync Cluster Assistant 在 200 GbE fabrics 上连接的两台 DGX Spark 64GB 系统将内存池化至 128GB。在单台设备上运行的相同工作流程无需重新配置软件环境即可扩展到两台设备。
Get Started With DGX Spark
开始使用 DGX Spark
DGX Spark 64GB is available from Acer, ASUS, Dell, Gigabyte, HP and MSI on Friday, Oct. 23, starting at $4,999.
DGX Spark 64GB 将于 10 月 23 日（星期五）起在 Acer、ASUS、Dell、Gigabyte、HP 和 MSI 上架，起售价为 4,999 美元。
To get started:
开始使用：
- Download a supported inference framework — llama.cpp, Ollama, vLLM or LM Studio.
- Download the recommended local model for the workflow.
- To scale to two units, connect them via their NVIDIA ConnectX-7 ports and launch NVIDIA Sync Cluster Assistant — it configures the network and routes workloads automatically.
- 下载支持的推理框架——llama.cpp、Ollama、vLLM 或 LM Studio。
- 下载适用于该工作流的推荐本地模型。
- 要扩展至两个节点，请通过其 NVIDIA ConnectX-7 端口连接它们，并启动 NVIDIA Sync Cluster Assistant——它会自动配置网络并路由工作负载。
For agentic AI playbooks on DGX Spark, visit the NemoClaw, OpenClaw, Hermes Agent and OpenShell pages on build.nvidia.com.
如需有关 DGX Spark 的 Agentic AI 操作指南，请访问 build.nvidia.com 上的 NemoClaw、OpenClaw、Hermes Agent 和 OpenShell 页面。
#ICYMI: More Updates From NVIDIA Local AI
#ICYMI：来自 NVIDIA Local AI 的最新动态
Explore playbooks on build.nvidia.com/spark for DGX Spark. The following playbooks are coming soon to 64GB devices:
探索 build.nvidia.com/spark 上关于 DGX Spark 的操作指南。以下操作指南即将支持 64GB 设备：
- Serve LLMs With vLLM
- Run OpenClaw With a Local LLM
- Connect Multiple DGX Sparks for Distributed Workloads
- 使用 vLLM 部署 LLM
- 使用本地 LLM 运行 OpenClaw
- 连接多个 DGX Spark 以处理分布式工作负载
New Windows PCs powered by NVIDIA RTX Spark are coming this month from Acer, ASUS, Dell, HP, Lenovo, Microsoft and MSI. Sign up for the RTX Spark newsletter to receive future updates.
本月，Acer、ASUS、Dell、HP、Lenovo、Microsoft 和 MSI 将推出搭载 NVIDIA RTX Spark 的新款 Windows PC。注册 RTX Spark 通讯订阅，以获取后续更新。
Alibaba’s Qwen-Image-2.1 brings image generation and editing together in a lightweight, open-weight model. It runs locally on NVIDIA RTX GPUs, DGX Spark and DGX Station, giving creators more ways to create and refine images on their own hardware.
阿里巴巴的 Qwen-Image-2.1 将图像生成与编辑功能整合到一个轻量级、开放权重的模型中。它可在 NVIDIA RTX GPU、DGX Spark 和 DGX Station 上本地运行，为创作者提供更多在其自有硬件上创建和精修图像的方式。
Follow NVIDIA RTX Spark on X, Instagram, TikTok and Facebook — and stay informed by subscribing to the NVIDIA Local AI newsletter. Follow NVIDIA Workstation on LinkedIn and X.
在 X、Instagram、TikTok 和 Facebook 上关注 NVIDIA RTX Spark——并通过订阅 NVIDIA Local AI 通讯保持了解最新动态。在 LinkedIn 和 X 上关注 NVIDIA Workstation。
See notice regarding software product information.
请参阅有关软件产品信息的声明。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力