NVIDIA DGX Spark is a compact desktop AI supercomputer (150 × 150 × 50.5 mm, 1.2 kg) described as a complete platform for local autonomous agents. At its core is the NVIDIA GB10 Grace Blackwell Superchip with a 20-core Arm CPU (10× Cortex-X925 + 10× Cortex-A725) and a Blackwell-architecture GPU with 5th-generation Tensor Cores and 4th-generation RT Cores.
The system delivers up to 1 PFLOP of FP4 compute, 128 GB of coherent unified LPDDR5x memory at 273 GB/s bandwidth, and 4 TB of self-encrypting NVMe M.2 storage. It can run models up to 200B parameters for inference and fine-tune models up to 70B parameters.
It includes a ConnectX-7 NIC (200 Gbps) that lets up to four DGX Spark systems be connected to work with models up to 700B parameters, plus Wi-Fi 7, Bluetooth 5.4 and 10 GbE. Use cases include prototyping, fine-tuning, inference, data science and edge application development.
AI Accelerator · serves as: High-level compute, AI Inference.
Which group NVIDIA DGX Spark belongs to and how it is built
Compute Modules is a subcategory of hardware components that provide processing power for robotic systems. It encompasses onboard computers, single-board computers (SBCs), AI accelerators, embedded processors, GPU/NPU compute modules, and other units responsible for processing sensor data and executing control logic. These modules form the foundation of modern autonomous, humanoid, and perception-capable robots.
An AI Accelerator is a specialized hardware component designed for efficient execution of artificial intelligence computations, particularly neural network inference, computer vision processing, and sensor data analysis. In robotics, AI accelerators are used to run perception models, object recognition, image segmentation, planning, and other tasks that require high computational throughput under constrained power budgets. They may take the form of dedicated NPU, TPU, VPU, or GPU chips, or specialized embedded modules.
