NVIDIA DGX Spark

Improve the performance of pre-trained models by fine-tuning on NVIDIA DGX Spark. With 128GB of unified system memory, fine-tune models up to 70 billion parameters to customize AI models and solutions for specific needs and use cases.

Fifth-generation Tensor Cores with support for FP4 deliver up to 1,000 TOPS of AI computing performance, combined with 128GB of system memory, accelerate inference of state-of-the-art AI models to test, validate and deploy from your NVIDIA DGX Spark.

From data preparation to model training, inference, and deployment, NVIDIA RAPIDS on NVIDIA DGX Spark simplifies the development process with Zero-code-change accelerators and familiar APIs to quickly accelerate existing workloads or rapidly develop specific use-case solutions, and easily scale out to data center or cloud.

DGX Spark provides an excellent platform for developing robotics, smart cities, and computer vision solutions. NVIDIA frameworks, including Isaac, Metropolis, and Holoscan,. These frameworks and tools enable developers to take advantage of the power of NVIDIA DGX Spark to quickly develop edge applications.