Local AI is becoming more useful as capable open models shrink to fit on more devices. Coming this month, NVIDIA DGX Spark will be available with 64 GB 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. The new SKU runs capable local agents on device—privately, without cloud dependency. When workloads grow, two units can cluster together via NVIDIA Sync Cluster Assistant without additional setup.
DGX Spark combines NVIDIA Grace Blackwell compute, unified memory, NVIDIA Connect X-7 networking and an NVIDIA CUDA-accelerated AI software stack in one system. The new 64 GB 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 128 GB model. It supports up to 100-billion-parameter models and agentic applications fully on device.
Two 64 GB units clustered together deliver up to 1.7x performance compared with a single system in NVIDIA's Qwen 3.8 27B test. 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 supported out of the box. Blender is among the first major creator application providers to support the platform.
Every DGX Spark ships with a built-in NVIDIA Connect X-7 NIC. Two units can connect directly with a QSFP cable, pooling memory to 128 GB and expanding model support to up to 200 billion parameters. The NVIDIA Sync app configures this multi-node cluster seamlessly. Coming at the end of the month, NVIDIA Sync Model Launcher makes running local AI as simple as clicking a few buttons.
Source: TechPowerUp News · Summarized by HeadlinesBriefing