What does the new 64GB DGX Spark change for local AI development?

A new entry point for personal AI supercomputing

DGX Spark combines Grace Blackwell compute with unified memory, ConnectX-7 networking, and a CUDA-accelerated AI software stack in one box. The compact system gives developers a place to experiment with models and their own data without spinning up a cloud instance for every task.

The 64GB configuration keeps the platform at an accessible price point. It retains the GB10 Grace Blackwell Superchip, DGX OS, and the full NVIDIA AI software stack. Support reaches up to 100-billion-parameter models and the agentic applications built on them, fully on device. 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.

Clustering without manual network setup

Every unit ships with a built-in ConnectX-7 NIC. Two units 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. The NVIDIA Sync app configures this multi-node cluster seamlessly. Its cluster assistant feature detects connected units, validates device configuration, then 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.

What runs out of the box

The system ships ready for agent development from day one. NVIDIA Agent Toolkit, CUDA-X AI libraries, and Nemotron open models are supported. Popular runtimes like Ollama, vLLM, and PyTorch with CUDA also work immediately. Developers can go from power-on to running models in minutes. Blender is among the first major creator application providers to support the platform, with a prebuilt, downloadable installer coming soon.

Three workflow examples illustrate the range. Keep a coding or research agent running on DGX Spark around the clock, ready to review code, analyze documents, or carry out multistep tasks. Run a language- or image-generation model on DGX Spark while using an agent or creative application on a laptop or desktop. When a single task outgrows one unit, 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.

Availability and what arrives next

Starting Friday, Oct. 23, the 64GB configuration is available from Acer, ASUS, Dell, Gigabyte, HP, and MSI at $4,999. To get started, download a supported inference framework such as llama.cpp, Ollama, vLLM, or LM Studio, then download the recommended local model for the workflow. To scale to two units, connect them via their ConnectX-7 ports and launch NVIDIA Sync Cluster Assistant — it configures the network and routes workloads automatically.

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. Playbooks for serving LLMs with vLLM, running OpenClaw with a local LLM, and connecting multiple DGX Sparks for distributed workloads are coming soon to 64GB devices. New Windows PCs powered by NVIDIA RTX Spark are also arriving this month from Acer, ASUS, Dell, HP, Lenovo, Microsoft, and MSI. Alibaba's Qwen-Image-2.1 brings image generation and editing together in a lightweight, open-weight model that runs locally on NVIDIA RTX GPUs, DGX Spark, and DGX Station.