{"slug": "nvidia-dgx-spark-64gb-gives-developers-more-ways-to-build-and-scale-local-ai", "title": "NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI", "summary": "NVIDIA will release a 64GB unified-memory configuration of its DGX Spark personal AI supercomputer this month through manufacturer partners Acer, ASUS, Dell, Gigabyte, HP and MSI, retaining the GB10 Grace Blackwell Superchip, DGX OS and full NVIDIA AI software stack of the 128GB model. The 64GB SKU supports up to 100-billion-parameter models on device, and two units can be clustered via NVIDIA Sync Cluster Assistant to pool 128GB of memory and support up to 200 billion parameters, delivering up to 1.7x performance versus a single system in NVIDIA's Qwen 3.8 27B test. NVIDIA Sync Model Launcher arrives at the end of the month to download and run Qwen3.8 27B on a single system or cluster and configure OpenCode for browser-based coding.", "body_md": "Local AI is becoming more useful by the token.\n\nAs 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.\n\nComing this month, [NVIDIA DGX Spark](https://www.nvidia.com/en-us/products/workstations/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.\n\nThe 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.\n\n## **A New Starting Point for Personal AI Supercomputing**\n\nDGX Spark combines NVIDIA Grace Blackwell compute, unified memory, [NVIDIA ConnectX-7 networking](https://www.nvidia.com/en-us/networking/ethernet-adapters/) and an [NVIDIA CUDA](https://developer.nvidia.com/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.\n\nThe compact, personal AI supercomputer provides a place to experiment with models and developers’ own data without turning to a cloud instance for every task.\n\nThe 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.\n\nTwo 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.\n\nDGX 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.\n\nBlender is among the first major creator application providers to support the platform, with a [prebuilt, downloadable installer coming soon](http://blender.org/download.).\n\n## **Scale Up With NVIDIA Sync Cluster Assistant**\n\nDevelopers 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.\n\nEvery 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.\n\nThe [NVIDIA Sync](https://docs.nvidia.com/sync/latest/index.html) 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.\n\nAnd 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.\n\n## **Developer Use Cases on DGX Spark** \n\nThe 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.\n\nHere are three workflow examples:\n\n- **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.\n- **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.\n- **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.\n\n## **Get Started With DGX Spark** \n\nDGX Spark 64GB is available from [Acer](https://www.acer.com/us-en/desktops-and-all-in-ones/veriton-workstations/veriton-gn100-ai-mini-workstation), [ASUS](https://www.asus.com/networking-iot-servers/desktop-ai-supercomputer/ultra-small-ai-supercomputers/asus-ascent-gx10/), Dell, [Gigabyte](https://www.gigabyte.com/AI-TOP-PC/GIGABYTE-AI-TOP-ATOM), HP and [MSI](https://ipc.msi.com/product_detail/Industrial-Computer-Box-PC/AI-Supercomputer/EdgeXpert-MS-C931) on Friday, Oct. 23, starting at $4,999.\n\nTo get started:\n\n- Download a supported inference framework — llama.cpp, Ollama, vLLM or LM Studio.\n- Download the recommended local model for the workflow.\n- 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.\n\nFor agentic AI playbooks on DGX Spark, visit [the NemoClaw](http://build.nvidia.com/spark/nemoclaw), [OpenClaw](http://build.nvidia.com/spark/openclaw), [Hermes Agent](http://build.nvidia.com/spark/hermes-agent) and [OpenShell](http://build.nvidia.com/spark/openshell) pages on build.nvidia.com. \n\n## **#ICYMI: More Updates From NVIDIA Local AI**\n\nExplore playbooks on [build.nvidia.com/spark](http://build.nvidia.com/spark) for DGX Spark. The following playbooks are coming soon to 64GB devices:\n\n- Serve LLMs With vLLM\n- Run OpenClaw With a Local LLM\n- Connect Multiple DGX Sparks for Distributed Workloads\n\nNew Windows PCs powered by [NVIDIA RTX Spark](https://blogs.nvidia.com/blog/local-ai-ifa-next-gen-agents-nv-pair-rtx-spark/) are coming this month from Acer, ASUS, Dell, HP, Lenovo, Microsoft and MSI. Sign up for the [RTX Spark newsletter](https://www.nvidia.com/en-us/products/rtx-spark/) to receive future updates. \n\nAlibaba’s [Qwen-Image-2.1](https://qwen.ai/blog?id=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.\n\n*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**.* \n\n*See* [*notice*](https://www.nvidia.com/en-eu/about-nvidia/terms-of-service/) *regarding software product information.*", "url": "https://wpnews.pro/news/nvidia-dgx-spark-64gb-gives-developers-more-ways-to-build-and-scale-local-ai", "canonical_source": "https://blogs.nvidia.com/blog/local-ai-dgx-spark-64gb-sync/", "published_at": "2026-10-02 13:00:39+00:00", "updated_at": "2026-10-02 13:08:35.291524+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-chips", "ai-agents", "ai-tools", "large-language-models"], "entities": ["NVIDIA", "NVIDIA DGX Spark", "NVIDIA Grace Blackwell", "NVIDIA ConnectX-7", "NVIDIA Sync Cluster Assistant", "NVIDIA Agent Toolkit", "Acer", "ASUS"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/nvidia-dgx-spark-64gb-gives-developers-more-ways-to-build-and-scale-local-ai", "markdown": "https://wpnews.pro/news/nvidia-dgx-spark-64gb-gives-developers-more-ways-to-build-and-scale-local-ai.md", "text": "https://wpnews.pro/news/nvidia-dgx-spark-64gb-gives-developers-more-ways-to-build-and-scale-local-ai.txt", "jsonld": "https://wpnews.pro/news/nvidia-dgx-spark-64gb-gives-developers-more-ways-to-build-and-scale-local-ai.jsonld"}}