ASUS ASCENT GX10 GB10 20-Core Arm CPU 128GB (On-Board) LPDDR5x NVIDIA Grace Blackwell GPU 4TB M.2 SSD DGX OS AI Workstation Mini PC

Description

FEATURES
Accelerate Local AI Workloads with 1000 TOPs AI Performance
Scale to 405B parameters by clustering two units with a QSFP/CX7 cable.
Enable 4-unit clustering with a 400GbE switch for larger deployments
NVIDIA GB10 Superchip Processor
20 Cores, 20 Threads
NVIDIA Grace Blackwell GB10 Graphics
5th Gen Tensor Cores, 4th Gen RT Cores
Supports Inferencing, RAG, Machine Learning Workloads
NVIDIA NIM, NVIDIA Blueprints Technology
Supports PyTorch, Jupyter, Ollama & More
128GB (On-Board) LPDDR5x Unified Memory
Support for up to 200 Billion Parameter Models (Single Mode)
Support for up to 405 Billion Parameter Models (ConnectX-7 Mode)
4TB M.2 2280 PCIe 5.0 x4 NVMe SSD
3x USB 20Gbps Type-C Ports with DisplayPort 2.1
1x USB 20Gbps Type-C Ports with Power Delivery 3.1
1x HDMI 2.1a (FRL) Port
10 Gigabit Ethernet RJ-45 LAN Port
2x NVIDIA ConnectX-7 Teaming Ports
WiFi 7 Dual-Band Adapter, Bluetooth 5.4
240W USB Type-C AC Adapter
NVIDIA DGX OS Pre-Installed
Supports Ubuntu Linux
Colour: Stellar Grey

TECHNICAL SPECIFICATIONS

Brand: ASUS
Series: ASCENT Series
Model: ASCENT GX10 Mini PC

Processor
Model: Grace Blackwell GB10 Superchip
Chipset Manufacturer: NVIDIA (Mediatek)
Boost Clock: N/A
Core Arrangement: 10x Cortex-X925 Arm Cores, 10x Cortex-A725 Arm Cores
Core Count: 20 cores
Thread Count: 20 threads
Cache: N/A
Lithography: TSMC N3 Process
Packaging: TSMC 2.5D Advanced Packaging Technology
Interconnect: NVIDIA NVLink Chip-to-Chip (NVLink-C2C)

AI Accelerator
Model: NVIDIA GB10 Superchip
Performance: Up to 1000 AI TOPS (CPU, GPU, NPU combined Int8)
Compatibility: Supports PyTorch, Jupyter, Ollama, & More

Memory
Total Installed: 128GB (On-Board)
Type: LPDDR5x
Speed: Up to 9400 MT/s
Maximum Capacity: 128GB (On-Board) LPDDR5x-9400
No SO-DIMM Slots available for upgrades

Graphics
Integrated: NVIDIA Grace Blackwell GB10 Graphics
CUDA Cores: 6144 CUDA cores
Tensor Cores: 5th Generation
RT Cores: 4th Generation
Tensor Performance: Up to 1 Petaflop
Graphics APIs: Shader Model 6.6, OpenGL 4.6, Vulkan 1.3
Compute APIs: CUDA 13.0, OpenCL 3.0
Memory: 128GB (Unified)
Workflow, Model & Tool Support: NVIDIA NIM, AI Blueprints, AI Workbench
Supported DL & ML Frameworks: PyTorch, Tensorflow, MATLAB & More
Supported Platforms: Riva, Holoscan, Metropolis, Isaac, & More
CUDA Support: cuDNN, cuBLAS, TensorRT, NCCL, & More
Hardware Support: 9th Gen NVIDIA Encoder Engines
6th Gen NVIDIA Decoder Engines
NVIDIA ConnectX-7

Storage
Installed: 1x 4TB M.2 2280 PCIe 5.0 x4 NVMe SSD
Supported: 1x M.2 2280 PCIe NVMe SSD Slot (Occupied)

Connectivity
Ports (Rear): 3x USB 20Gbps Type-C Ports with DisplayPort 2.1
1x USB 20Gbps Type-C Ports with Power Delivery 3.1
1x HDMI 2.1a (FRL) Port
1x 10 Gigabit Ethernet RJ-45 LAN Port
2x NVIDIA ConnectX-7 Teaming Ports
Buttons: Power Button (Front)

Networking
Ethernet: 10 Gigabit Ethernet RJ-45 LAN Adapter
Wi-Fi: WiFi 7 Dual-Band Adapter
Bluetooth: Bluetooth 5.4

General
Operating System: NVIDIA DGX Operating System
Supports Ubuntu Linux
Power Adapter: 240W AC Adapter, Universal 110-230V, 50-60Hz
Dimensions: 150 x 150 x 51mm (W x D x H)
Weight: 1.48kg
Colour: Stellar Grey