NVIDIA DGX Spark Personal AI Supercomputer | GB10 Grace Blackwell | 128GB Unified Memory
The NVIDIA DGX Spark represents a new era of personal AI computing. Built on the groundbreaking NVIDIA GB10 Grace Blackwell Superchip, it delivers extraordinary AI performance in a compact desktop form factor designed for developers, researchers, enterprises, and AI innovators. Whether you're fine-tuning large language models, building autonomous AI agents, performing local inference, or accelerating machine learning workflows, DGX Spark provides the power of enterprise AI infrastructure directly from your workspace. Up to 1 PFLOPS of AI computing performance NVIDIA GB10 Grace Blackwell Superchip 128GB coherent unified memory architecture Supports AI models up to 200 billion parameters locally ConnectX-7 high-performance networking 4TB self-encrypting NVMe storage Designed for AI training, fine-tuning and inference Seamless deployment from desktop to cloud and data center
MSI EdgeXpert MS-C931 AI Supercomputer
Powered by NVIDIA GB10 Grace Blackwell architecture for next-gen AI workloads. Delivers up to 1 petaFLOP (FP4 Sparse) AI performance. Features 20-core Arm CPU (10x Cortex-X925 + 10x Cortex-A725). Utilizes NVLink-C2C interconnect for ultra-fast CPU-GPU communication. Equipped with 128GB LPDDR5x unified memory for large AI models. Built as a full-stack AI platform (hardware + NVIDIA DGX OS software). Ideal for AI developers, deep learning, LLM inference, and edge deployment.
