مميزات خاصة

LOCAL LLM DEVELOPMENT AND INFERENCE: Built for AI developers and machine learning engineers who want to prototype, test and run generative AI locally. The GB10 Grace Blackwell Superchip and 128GB unified memory are designed to support inference with models up to 200 billion parameters and fine-tuning with models up to 70 billion parameters.
AI AGENTS, RAG AND CODING WORKFLOWS: Create private chatbots, coding assistants, autonomous agents, tool-using applications and retrieval-augmented generation systems. Local processing reduces dependence on cloud APIs and gives developers greater control over models, data, latency and ongoing usage costs.
RESEARCH, DATA SCIENCE AND MODEL EXPERIMENTATION: A compact development platform for researchers, data scientists, universities and laboratories working with PyTorch, Jupyter, CUDA and other supported tools. Use it for model evaluation, data analysis, proof-of-concept development, quantization and supported fine-tuning workflows.
ROBOTICS, COMPUTER VISION AND EDGE AI: Suitable for developers creating robotics, smart-camera, computer-vision, industrial automation and edge AI applications. Prototype perception pipelines, multimodal models and intelligent systems locally before moving validated workloads to compatible production infrastructure.
PRIVATE ON-PREMISES AI FOR TEAMS: Designed for startups, enterprises and professional creators that need to keep proprietary code, models and sensitive datasets within their own environment. Its compact desktop form factor, 10Gb Ethernet and ConnectX-7 networking make it practical for offices, laboratories and multi-system AI development.

وصف

DGX Spark Personal AI Supercomputer
Bring advanced AI development directly to your desk with DGX Spark. Powered by the GB10 Grace Blackwell Superchip, this compact system combines a Blackwell architecture GPU, fifth-generation Tensor Cores and a 20-core Arm processor to deliver up to 1 PFLOP of FP4 AI performance with sparsity.

128GB Coherent Unified System Memory
The 128GB LPDDR5x unified memory architecture allows the CPU and GPU to access a shared memory pool, reducing traditional data-transfer bottlenecks. DGX Spark is designed to support local inference with AI models up to 200 billion parameters and model fine-tuning with up to 70 billion parameters.

Built for Local AI Development
Use DGX Spark to prototype generative AI applications, develop autonomous agents, run local large language models, perform retrieval-augmented generation, fine-tune supported models and work with data science or edge AI applications. Local processing can also help keep proprietary models and sensitive project data within your own environment.

DGX OS and AI Software Environment
The system runs DGX OS, a Linux-based environment designed for accelerated AI workloads. It supports CUDA and popular AI development tools and frameworks, including PyTorch, Jupyter, NIM and NeMo. Projects developed locally can be prepared for deployment across compatible accelerated computing infrastructure.

Advanced Connectivity
Connect to high-speed networks and compatible peripherals through 10Gb Ethernet, Wi-Fi 7, Bluetooth 5.4, USB-C ports, HDMI output and ConnectX-7 networking. Compatible DGX Spark systems can also be connected for larger-scale AI workflows.

Compact Desktop Design
Measuring approximately 5.9 x 5.9 x 2 inches, DGX Spark delivers advanced AI computing capabilities in a compact, energy-efficient form factor suitable for offices, laboratories, classrooms and development environments.

Compatibility Notice
DGX Spark uses an Arm-based processor and a Linux-based operating system. It is designed primarily for AI developers, researchers, data scientists and technically experienced users. It is not a standard Windows desktop PC, and software requiring Windows or an x86 processor may not be compatible.

What Is Included
DGX Spark Personal AI Supercomputer with seller-configured 2TB NVMe SSD, USB-C power adapter and power cable.

مرحبًا،

بحث

مميزات خاصة

وصف

منتجات شبيهه