ASUS Ascent GX10 AI Supercomputer, NVIDIA GB10 Grace Blackwell, 1 petaFLOP AI, 128GB Unified Memory, 4TB Gen4 SSD, Wi-Fi 7, BT 5.4, NVIDIA NVLink-C2C, NVIDIA DGX OS, NVIDIA ConnectX-7 | 90MS0371-M00 0X0

GeForce RTX 50 Series - Game Changer! The Most Advanced AI platform for Gamers, Creators and beyond. Multiply performance with NVIDIA DLSS 4.5, generate images at unprecedented speed, and unleash your creativity with NVIDIA Studio.

Revolutionizing Research: ASUS Ascent GX10 Compact AI Supercomputer

The ASUS Ascent GX10 redefines desktop AI capability, packing the power of a data center into a compact, deployable system. It is the ultimate tool for accelerating AI development, research, and edge computing across labs and offices.

Agentic AI

Secure and Scalable Agentic AI with NVIDIA NemoClaw

The ASUS Ascent GX10 with the NVIDIA NemoClaw open source stack, adds privacy and security controls to OpenClaw. NemoClaw installs NVIDIA OpenShell to enforce policy-based privacy and security guardrails, giving users control over how agents behave and handle data and provides the compute resources to run open models like NVIDIA Nemotron locally for enhanced privacy and cost efficiency.

Power Agentic AI Locally Without Perpetual Token Costs

The ASUS Ascent GX10, featuring 1 petaFLOP of AI performance and 128GB of memory, empowers you to run agentic AI (such as OpenClaw¹ or other frameworks) on-demand. By leveraging local execution of your preferred AI models, you achieve greater cost predictability², enterprise-grade stability, and enhanced mitigation against unintended data exposure³

• 24/7 Continuous AI Execution
• Reduced API Dependency
• On-Premises Data Sovereignty

Extreme, Uncompromised AI Power:

• NVIDIA GB10 Superchip: At its core is the NVIDIA GB10 Grace Blackwell Superchip, providing unmatched computational horsepower.
• 1 PetaFLOP Performance: Delivers a massive 1 petaFLOP of AI performance, enabling rapid training, inference, and analysis on demanding AI models.
• 128GB Unified Memory: Features 128GB of Coherent Unified System Memory, essential for handling and fine-tuning models up to 200B parameters efficiently.

Advanced Architecture and Scalability:

• NVIDIA NVLink-C2C: Utilizes this ultra-fast interconnect for high-speed CPU-GPU memory communication, minimizing latency.
• NVIDIA ConnectX-7 Networking: Ensures superior data throughput and low latency, crucial for multi-system collaboration and data ingestion.
• Stackable Design: The GX10 architecture supports dual system stacking, unlocking superior scalability and performance for larger projects.

Developer-Ready and Efficient:

• Full Stack AI Solution: Comes pre-loaded with NVIDIA DGX OS with Ubuntu Linux, providing a developer-optimized platform with full-stack compatibility for streamlined workflows.
• High-Capacity Storage: Equipped with a large 4TB M.2 NVMe PCIe 4.0 SSD for high-speed data access and storage, accommodating large datasets and models.

• Minimal Footprint: The compact desktop design with advanced thermal engineering ensures sustained high performance and reliability in space-constrained environments.