Ultra-Small AI SupercomputerASUS Ascent GX10
Based on NVIDIA DGX Spark™
The ASUS Ascent GX10, accelerated by the NVIDIA GB10 Grace Blackwell Superchip and the NVIDIA AI software stack, provides a full-stack solution for AI development and deployment. Its compact design facilitates seamless integration and deployment, enabling powerful AI performance for innovators who demand excellence. With advanced AI tools and NVIDIA® ConnectX®-7, this small-scale server enhances your AI capabilities while empowering your unique solutions.
-
NVIDIA® GB10 Grace Blackwell Superchip
-
Up to
128GB Unified Memory
Available in 64GB and 128GB configurations
-
1 petaFLOP
AI Performance
-
-
NVIDIA®
NVLink™-C2CDeliver a cohesive CPU+GPU memory model with five times the bandwidth of PCIe Gen 5
-
NVIDIA DGX™ OS with Ubuntu Linux
-
NVIDIA® ConnectX®-7
Allows two GX10 systems to be linked for handling even larger models
-
Optimized Cooling Design
-
NVIDIA AI Software Stack
-
Al Development Environment
Includes NVIDIA NIM™ and Blueprints. Supports Pytorch, Jupyter, Ollama for prototyping and inference.
video about ASUS Ascent GX10 | ASUS AI Supercomputer
Design
Revolutionary AI Performance on Your Desktop
The groundbreaking ASUS Ascent GX10 AI Supercomputer, powered by the state-of-the-art NVIDIA® GB10 Grace Blackwell Superchip found in the NVIDIA DGX Spark, brings petaflop-scale AI computing capabilities directly to the desks of developers, AI researchers, and data scientists. This innovative device is designed to empower local AI development with its exceptional performance and advanced features.
Compact, Powerful, and Scalable
Compact Size 150 x 150 x 51mm
Unparalleled AI Performance
Up to 1 petaFLOP of AI performance using FP4
Delivers up to 1 petaFLOP of AI performance to power large AI workloads.
64GB or 128GB of LPDDR5x Coherent Unified System Memory
Empowers model development, experimentation, and inferencing with ample memory capacity.
-
Up to
1 petaFLOP
of AI Performance
Using FP4 -
Up to
128G
Coherent Unified
System Memory
Cutting-Edge Architecture
NVIDIA GB10 Grace Blackwell Superchip:
Central to the ASUS Ascent GX10, this advanced chip features a robust Blackwell GPU with fifth-generation Tensor Cores and FP4 support.
High-Performance 20-Core Arm CPU:
Enhances data preprocessing and orchestration, accelerating model tuning and real-time inferencing.
NVLink™-C2C Technology:
Provides a cohesive CPU+GPU memory model with five times the bandwidth of PCIe 5.0.
Performance
Handles Large Parameter Gen AI Models
Support for AI Models Up to 200 Billion Parameters
Prototype, fine-tune, and infer the latest AI reasoning models directly on your desktop — run models up to 100-billion parameters on the 64GB configuration, or scale up to 200-billion parameters on the 128GB configuration.
Integrated NVIDIA® ConnectX®-7 Network Technology
Cluster up to four systems with NVIDIA Sync for larger memory pool (256 GB for the 64 config) and 512 GB for the 128 config) and up to 4 petaFLOP to run frontier-scale models and more complex agents.
AI Networking
Meets Next-Gen Connectivity: NVIDIA® ConnectX-7
The ASUS Ascent GX10 integrates NVIDIA® ConnectX-7 to deliver ultra-high-speed networking, enabling rapid data transfer and low-latency communication across distributed AI workloads.
Ultra-Fast AI Data Throughput
Ultra-fast bandwidth ensures rapid data transfer between nodes, perfect for large-scale distributed AI workloads.
Secure, Intelligent Networking
Built-in hardware acceleration for TLS, IPsec, and MACsec ensures encrypted data transmission without CPU overhead.
Precision-Critical Performance
IEEE 1588v2 PTP support enables microsecond-level time synchronization for time-sensitive AI and edge computing applications.
AI Experience
Integrated AI Software Stack for Seamless Development
Preloaded AI for Instant Development
NVIDIA DGX OS (Ubuntu-based) – Optimized AI environment, ready to use.
NVIDIA AI Software Stack – Preloaded frameworks, SDKs, and tools for fast deployment.
Optimized AI Tools & AI Frameworks
CUDA, PyTorch, TensorFlow, Jupyter – Optimized for AI model development & inference.
NVIDIA TensorRT – High-performance AI inference engine.
NVIDIA NIMs & Blueprints – Prebuilt AI workflows & microservices.
Industry-Leading AI Model Support
DeepSeek R1 – AI inference optimized up to 100B parameters, an ideal fit for the 64GB configuration.
Generative AI — frontier-scale models up to 512GB pooled memory (4x GX10 128GB with NVIDIA Sync).
Meta, Google models – Broad compatibility with industry-leading AI frameworks.
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.
View On GitHub Try It Now
Power Agentic AI Locally Without Perpetual Token Costs
The ASUS Ascent GX10, featuring 1 petaFLOP of AI performance and 64GB or 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
Disclaimers
- ASUS Ascent GX10 supports and is compatible with third-party open-source software, OpenClaw, Hermes Agent…etc.
OpenClaw is a trademark/product of its respective owners. - API dependency refers to the local execution of open-source models (e.g., Llama, Qwen) using the ASUS Ascent GX10's onboard hardware. Third-party services, premium licensed models, or web-based plugins may still incur separate fees from their respective providers. Saving regarding API tokens are illustrative and depend on user-specific workflows and the choice of local open-source models. ASUS does not provide API keys or licenses for third-party proprietary models. Users are responsible for ensuring compliance with the terms of service of any deployed AI models and third-party software integrated with OpenClaw or other frameworks.
- Data exposure may occur if network access or third-party services are configured. Based on default local configuration with no external endpoints enabled.
NVIDIA Personal AI Router (PAIR)
One Personal AI Network with NVIDIA® PAIR
With NVIDIA® PAIR (Personal AI Router), the ASUS Ascent GX10 becomes the anchor of your own personal AI cluster — routing inference requests across every RTX GPU, Mac, and Windows PC you own through one endpoint. This helps you maximize local compute while keeping prompts, files, and agent context private, with no cloud round-trip required.
Download Now
Thermal
Precision-Crafted for Ultimate Thermal Efficiency
Tackle AI's most demanding workloads with the ASUS Ascent GX10. Its advanced dual-fan design with 7-level control delivers smooth, precise airflow. With 1.6× more efficient thermal coverage than comparable compact systems, the GX10 stays cooler and consistently performs at its peak.
Scalable
Stack More, Multiply Your AI Power
Two 64GB units pool to 128GB of memory and up to 2 petaflops of AI compute — up to 1.7x the performance of a single 128GB unit, with no server rack required.
Two 128GB units pool to 256GB of memory; scale to four for 512GB and up to 4 petaflops of AI compute, for running frontier-scale models and more complex agents. NVIDIA Sync makes clustering and managing systems easy.*
*Clustering four systems requires an external switch."
Sources: NVIDIA Sync — Cluster Assistant, Connect Multiple DGX Spark through a Switch
Connectivity
I/O Ports
1Kensington Lock Slot
21 x USB 3.2 Gen 2x2 Type-C, 20Gbps,
alternate mode (DisplayPort 2.1), with PD in(180W EPR PD3.1 SPEC)
33 x USB 3.2 Gen 2x2 Type-C, 20Gbps,
alternate mode (DisplayPort 2.1)
4HDMI 2.1b port
510 GbE LAN
6NVIDIA ConnectX®-7 NIC
Application
Local Development, Scalable Deployment
Seamless Transition to Cloud
Leverage NVIDIA AI platform software architecture to move models from desktop environments to DGX Cloud or any accelerated cloud or data center infrastructure with minimal code adjustments.
Cost-Effective Experimentation Platform
Free up essential compute resources in clusters better suited for training and deploying production models.
Prototyping
Fine Tuning / Inference
Data Science
Explore More with ASUS Ascent
Discover more ways to experience ASUS Ascent — from staying informed about future innovations to testing AI workloads on real hardware and exploring special offers.
Stay Informed About Future Innovations
Be the first to know about upcoming ASUS Ascent products, technologies, and innovations.
*Specifications and product images are subject to change.
Explore Special Offers
Higher education institutions and active NVIDIA Inception members may be eligible for special offers on ASUS Ascent GX10.
Cases Studies
FAQ
-
What memory configurations are available for ASUS Ascent GX10?What memory configurations are available for ASUS Ascent GX10? ASUS Ascent GX10 is available with 64GB or 128GB of coherent unified system memory, providing flexible options for different AI development, experimentation, and inference workloads.
-
What software and tools are included with the ASUS Ascent GX10?What software and tools are included with the ASUS Ascent GX10? The Ascent GX10 comes pre-loaded with NVIDIA AI software stack, which developers can use frameworks such as PyTorch, TensorFlow, JAX, Ollama. The NVIDIA AI Software Stack also allows users to run open source model on the system.
-
Can multiple Ascent GX10 be clustered for greater AI model capacity?Can multiple Ascent GX10 be clustered for greater AI model capacity? For larger LLM fine-tuning or high performing simulation and scientific computing, sometimes you might need to scale the workload of your Ascent GX10 unit. A maximum of four GX10 can be clustered together to scale the workloads beyond a single unit. Employ the integrated NVIDIA ConnectX-7 Network Technology to enable clustering.
-
What are the main differences between the Ascent GX10 and NVIDIA DGX Spark?What are the main differences between the Ascent GX10 and NVIDIA DGX Spark? The ASUS Ascent GX10 showcases meticulous engineering with a thermal design built to handle demanding workloads effortlessly. Every element of its cooling system reflects careful craftsmanship, ensuring sustained high performance in an impressively compact form.
-
What AI applications does the Ascent GX10 support?What AI applications does the Ascent GX10 support? The Ascent GX10 supports a wide range of AI workloads. In generative AI, it enables fine-tuning and running large language models (LLMs) for advanced chatbots and virtual assistants. It also excels in computer vision tasks such as object detection and tracking, as well as predictive analytics for risk assessment and demand forecasting. Finally, the GX10 is well-suited for simulation and research, making it a versatile AI computing solution for multiple industries.
-
Can I use Ascent GX10 for education?Can I use Ascent GX10 for education? With up to 1 petaFLOP of AI performance, ASUS Ascent GX10 provides institutions, educators, and students the chance to experience hands-on AI training, model fine-tuning, and deploying large scale AI models. Users can now prototype and experiment with models right on campus, instead of solely depdent on cloud resources.
-
Can I use Ascent GX10 for enterprise?Can I use Ascent GX10 for enterprise? Ascent GX10 is a compact AI supercomputer that removes the barrier to high-performance AI computing by enabling local AI workloads and avoiding recurring cloud computing costs, all while keeping data confidential. With the compact 1.6L chassis, it's designed to fit into standard office environments. Whether you're in manufacturing, retail, finance, healthcare, or technology, Ascent GX10 enables faster insights and efficient operations.
-
What warranty does the ASUS Ascent GX10 include?What warranty does the ASUS Ascent GX10 include? The ASUS Ascent GX10 comes with a 1-year limited hardware warranty that covers defects in materials and workmanship from the date of purchase.
-
Can ASUS Ascent GX10 run OpenClaw?Can ASUS Ascent GX10 run OpenClaw? Yes, ASUS Ascent GX10 is a compact AI supercomputer delivering up to 1 petaFLOP of AI performance and 128GB of unified memory for large-scale workloads. It supports Agentic AI frameworks such as OpenClaw and Hermes Agent, enabling a fully local AI system with predictable cost, enterprise-grade stability, and secure data privacy.
-
What's the difference between the 64GB and 128GB Ascent GX10, and which should I choose?What's the difference between the 64GB and 128GB Ascent GX10, and which should I choose? The 64GB configuration supports models up to 100 billion parameters — comfortably covering today's most popular agentic models in the 30–35B range — entirely on-device, at a lower price point. The 128GB configuration works with models up to 200 billion parameters locally, for teams building with larger or fine-tuned models. Both share the same NVIDIA GB10 Grace Blackwell Superchip and 1 petaFLOP of AI performance, and either can be clustered with additional units — up to four, via NVIDIA Sync — for pooled memory and compute.
