MSI today announced a 64 GB configuration of its EdgeXpert desktop AI supercomputer, based on the NVIDIA DGX Spark platform. Grounded in proven deployments across legal IP governance, factory intelligence, offline voice translation, and agentic workflows, the 64 GB model complements the existing 128 GB tier to give enterprises a cost-effective path to scale AI agents. NVIDIA Sync helps teams set up a cluster of connected systems and monitor CPU and GPU activity from one desktop app.

Always-On Agentic AI at the Edge
As AI evolves from chatbots to autonomous agents, workloads require 24/7 residency, multistep reasoning, and direct access to local data. Based on the NVIDIA DGX Spark platform (1 petaFLOP FP4 AI compute), the MSI EdgeXpert 64 GB model runs up to 100B parameter open-source models entirely inside the firewall:

• Manufacturing: Drives visual quality inspection agents for real-time defect detection and corrective actions.
• Banking & Legal: Powers fraud investigation and audit agents with total data sovereignty.
• Healthcare & Retail: Hosts clinical documentation and inventory agents close to operational data.

Two Tiers, One Platform: Develop Big, Deploy Lean

Eunice Huang, Vice President of MSI IPC"Agentic AI has been moving from proof of concept to production, changing what enterprises need from infrastructure. The 128 GB EdgeXpert serves development teams running 200B parameter models or fine-tuning up to 70B parameters. The new 64 GB model targets deployment-first organizations scaling agents across sites where unit cost efficiency dictates reach."

A typical rollout begins with 128 GB units in HQ AI Centers, then expands to fleets of 64 GB units at branch offices, factory floors, retail locations, and regulated environments.

Key Features

• 64 GB LPDDR5x unified memory (supports models up to 100B parameters)
• Superior Thermal: Engineered for sustained performance in always-on workloads
• Compact Footprint: 1.2-liter, 1.2-kg desktop design with whisper-quiet cooling
• Enterprise Connectivity: 10GbE networking and 200GbE NVIDIA ConnectX-7 NIC for system clustering.
• Turnkey Software: Pre-installed NVIDIA DGX OS and full NVIDIA AI software stack
• On-Premises Inference: Zero data leakage, full compliance, and predictable TCO

Availability
The EdgeXpert 64 GB model will be available on October 23, 2026.