ASUS Ascent GX10 1TB NVIDIA GB10 DGX-Based Desktop AI Supercomputer
ASUS Ascent GX10 Desktop AI Supercomputer, GB10 Blackwell Superchip, 128GB LPDDR5X, 1TB SSD, ConnectX-7, 1000 TOPS
Email me when the availability or price changes
Suggested Alternatives
Ascent GX10 NVIDIA® GB10 Compact Desktop AI Supercomputer from ASUS
Ultra-Small AI Supercomputer The ASUS Ascent GX10, powered by the NVIDIA GB10 Grace Blackwell Superchip and the NVIDIA AI software suite, delivers a complete platform for AI creation and execution. Its streamlined, space-saving design ensures easy integration and rapid deployment, bringing exceptional AI performance to visionaries seeking top-tier results. Equipped with cutting-edge AI tools and NVIDIA® ConnectX®-7 networking, this compact server boosts AI potential while supporting your unique innovations.
Revolutionary AI Performance On Your Desktop
The revolutionary ASUS Ascent GX10 AI Supercomputer, driven by the cutting-edge NVIDIA® GB10 Grace Blackwell Superchip (featured in the NVIDIA DGX Spark), delivers petaflop-scale AI computing power to the workstations of developers, researchers, and data scientists. Built to advance local AI innovation, this powerful system combines exceptional performance with sophisticated features to accelerate progress in AI development.
Compact. Powerful. Scalable.
Compact Size 150 x 150 x 51mm
Unparalleled AI Performance Up to 1 petaFLOP of AI performance using FP4 Delivers 1 petaFLOP of AI performance to drive demanding AI computing tasks. 128 GB LPDDR5x Coherent Unified System Memory Empowers advanced model development, experimentation, and efficient inferencing with ample and reliable memory capacity.
Up to
1 petaFLOP
of AI Performance
Using FP4
128G
Coherent Unified
System Memory
Cutting-Edge Architecture NVIDIA GB10 Grace Blackwell Superchip: At the core of the ASUS Ascent GX10 is a high-performance Blackwell GPU, boasting fifth-generation Tensor Cores and FP4 support. High-Performance 20-Core Arm CPU: Optimises data preprocessing and workflow orchestration, speeding up model tuning and real-time inference. NVLink™-C2C Technology: Delivers a cohesive CPU and GPU memory architecture offering fivefold the bandwidth of PCIe 5.0.
Handles Large Parameter Gen AI Models
Use, train & experiment with Large-scale AI models
Support for AI Models 200 Billion Parameters Design, refine, and infer cutting-edge AI reasoning models right from your desktop.
Integrated NVIDIA® ConnectX®-7 Network Technology Connect two ASUS Ascent GX10 units to tackle larger-scale models, including Llama 3.1 with 405 billion parameters.
Next-Gen AI Networking with: NVIDIA® ConnectX-7
The ASUS Ascent GX10 features NVIDIA® ConnectX-7, providing ulta-high-speed networking for fast data transfer and minimal latency when handling distributed AI workloads.
Ultra-Fast AI Data Throughput With bandwidth of up to 200Gb/s, data moves lightning-fast between nodes - perfect for large-scale, distributed AI tasks.
Secure, Intelligent Networking Integrated hardware acceleration for TLS, IPsec, and MACsec secures data in transit while eliminating CPU overhead.
Precision-Critical Performance Support for IEEE 1588v2 PTP delivers microsecond-precision time sync for time-critical AI and edge computing workloads.
Integrated AI Software Stack for Seamless Development
The ASUS Ascent GX10 uses NVIDIA® ConnectX-7 to provide ultra-fast networking, ensuring rapid data transfer and low-latency communication for distributed AI workloads.
Preloaded AI for Instant Development NVIDIA DGX OS (Ubuntu-based) – Optimised AI environment, ready to use.
NVIDIA AI Software Stack – Preloaded frameworks, SDKs, and tools for fast deployment.
Optimised AI Tools & AI Frameworks CUDA, PyTorch, TensorFlow, Jupyter – Optimised for AI model development & inference.
NVIDIA TensorRT – High-performance AI inference engine.
NVIDIA NIMs & Blueprints – Prebuilt AI workflows & microservices.
Industry-Leading AI Model SupportDeepSeek R1 – AI inference optimised up to 70B parameters.
Llama 3.1 – Generative AI up to 405B parameters (dual-GX10).
Meta, Google models – Broad compatibility with industry-leading AI frameworks.
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.
Agentic AI Agentic AI applies advanced reasoning and adaptive planning to independently tackle complex, multi-step challenges.
OpenClaw Open-source, self-hosted AI agent platform that runs locally to automate complex tasks and manage emails, calendars, and files.
NVIDIA NemoClaw Adds privacy and security controls to OpenClaw. With one command, anyone can run always-on, self-evolving agents anywhere.
Engineered for Maximum Efficiency
Optimised Cooling Design Ensures sustained AI performance under heavy workloads. Compact Form Factor Delivers high-density AI computing in a small footprint.
Connectivity
