xFusion FusionXpark GB10 | 20 core Arm CPU | 128 GB LPDDR5x | 4 TB NVMe | NVIDIA DGX OS | 1-year warranty
- NVIDIA Grace Blackwell GB10 Superchip, up to 1 PetaFLOP AI (FP4)
- 20-core Arm CPU (10x Cortex-X925 + 10x Cortex-A725)
- 128 GB LPDDR5x unified system memory
- 4 TB NVMe M.2 SSD, self-encrypting
- Wi-Fi 7, Bluetooth 5.4, 10GbE LAN and USB4 Type-C
- NVIDIA DGX OS
- 1.2 kg Weight
- 1-year limited warranty
Free Shipping
Zero delivery charges, maximum convenience.
If You Have Any Query,
Please Contact Us
Our Sales Specialist
Name: Anjalina
Physical Store Available
100% Genuine
24/7 Support
Description
Dedicated Platform for Effortless AI Workloads
FusionXpark GB10, A new desktop Al computer specifically designed for the complete construction and operation of Al. It utilizes the NVIDIA GB10 Grace Blackwell superchip, providing up to 1000 AI TOPS performance with energy efficiency and a compact design to power large Al workloads. With 128GB of unified address system memory, developers can proto-type, fine-tune, or infer next-generation Al models with up to 200 billion parameters and seamlessly deploy them to data centers or cloud platforms. Additionally, the integrated NVIDIA Connect™ network allows two Al computers to be connected, supporting inference on models with up to 405 billion parameters.
With its outstanding energy efficiency and compact design, this Al computer offers powerful Al supercomputing capa-bilities and superior performance, making it the ideal choice for Al developers, researchers, and data scientists.
AI Assistant for Developers
Mainstream ecosystem of FusionXpark GB10 support, with one-stop workflow from model prototyping, fine-tuning, inference to AI agent deployment.
Local AI Deployment
Ensuring data privacy and accelerating productivity, applicable to scenarios such as predictive maintenance, medical image analysis, and financial forecasting.
Efficient Research and Education
Effortless AI teaching platform setup, delivering “personal supercomputing” research experience with agile teaching and training.
Edge Applications
End-to-end development of edge AI applications on desktop for real-time responsiveness and edge computing capability.
Diverse Interfaces for Ultrafast Interconnect
| Architecture | NVIDIA Grace Blackwell |
| GPU | NVIDIA Grace Blackwell GB10 Superchip, up to 1 PetaFLOP AI (FP4), 6144 CUDA/Tensor/RT cores |
| CPU | 20-core Arm (10x Cortex-X925 + 10x Cortex-A725) |
| CUDA Cores | 6,144 CUDA Cores |
| Tensor Cores | 5th Generation |
| RT Cores | 4th Generation |
| Tensor Performance | 1 PFLOPS |
| System Memory | 128GB LPDDR5x Unified Memory |
| Memory Interface | 256-bit |
| Memory Bandwidth | 273 GB/s |
| Storage | 4 TB NVME.M2 with self-encryption |
| USB | 4x USB TypeC |
| Ethernet | 1x RJ-45 connector 10 GbE |
| NIC | ConnectX-7 Smart NIC |
| Wi-Fi | WiFi 7 |
| Bluetooth | BT 5.4 |
| Audio-output | HDMI Multi-channel Audio Output |
| Display Connectors | 1 × HDMI 2.1a |
| NVENC | NVDEC | 1x | 1x |
| OS | NVIDIA DGX™ OS |
| System Dimensions | 150 mm L x 150 mm W x 50.5 mm H |
| System Weight | 1.2 kg |
| Warranty | 1-year warranty |
| Question | What is the xFusion FusionXpark GB10? |
| Answer | The xFusion FusionXpark GB10 is a compact AI computing platform powered by the NVIDIA GB10 Grace Blackwell Superchip. It is designed for AI development, model prototyping, fine-tuning, inference, and AI agent workloads. |
| Question | What processor does the FusionXpark GB10 use? |
| Answer | The FusionXpark GB10 uses a 20-core Arm CPU with 10 Cortex-X925 cores and 10 Cortex-A725 cores, integrated into the NVIDIA Grace Blackwell architecture. |
| Question | How much memory does the xFusion FusionXpark GB10 have? |
| Answer | The FusionXpark GB10 comes with 128GB LPDDR5x unified system memory. Its unified memory architecture is designed to support demanding local AI development and inference workloads. |
| Question | How powerful is the FusionXpark GB10 for AI workloads? |
| Answer | The FusionXpark GB10 delivers up to 1 PFLOP of Tensor performance at FP4 precision, using the NVIDIA Grace Blackwell architecture. It supports AI workloads including model development, inference, and fine-tuning. |
| Question | What AI models can run on the FusionXpark GB10? |
| Answer | With 128GB of unified memory, the GB10 platform is designed to run and develop AI models with large parameter counts locally. xFusion states that FusionXpark can support inference on models of up to 200 billion parameters and fine-tuning of models up to 70 billion parameters. |
| Question | Is FusionXpark GB10 suitable for AI developers and researchers? |
| Answer | Yes. FusionXpark GB10 is designed for AI developers, researchers, and data scientists working with model prototyping, fine-tuning, inference, AI agents, and local AI applications. Its compact form factor also makes it suitable for desktop AI development environments. |
| Question | What storage options are available on the FusionXpark GB10? |
| Answer | The FusionXpark GB10 supports 1TB, 2TB, and 4TB self-encrypting NVMe M.2 storage configurations, providing high-speed local storage for AI models, datasets, applications, and development environments. |
| Question | Can FusionXpark GB10 be used for local AI deployment? |
| Answer | Yes. FusionXpark GB10 is designed for local AI deployment where organizations need to develop and run AI workloads locally. This can be useful for applications such as predictive maintenance, medical image analysis, financial forecasting, and other workloads where local processing and data privacy are important. |
| Question | How does FusionXpark GB10 compare with a conventional workstation for AI development? |
| Answer | FusionXpark GB10 is purpose-built around the NVIDIA Grace Blackwell platform and combines GPU acceleration, unified memory, NVIDIA DGX OS, and AI software support in a compact system. Its 128GB unified memory and up to 1 PFLOP FP4 Tensor performance make it particularly suited to local AI development and inference rather than general-purpose workstation workloads. |
Physical Store Available
100% Genuine
24/7 Support
