NVIDIA DGX Spark Developer Kit Turns a Desk Into a Supercomputing Lab
Web page · https://blogs.nvidia.com/blog/dgx-spark-hpc-developer-kit-sc26
At SC26, an annual supercomputing conference taking place this week in Chicago, NVIDIA is introducing the DGX Spark HPC Developer Kit for researchers, academics and developers. The kit is a four-node cluster of NVIDIA DGX Spark systems, each connected directly to its two neighbors in a ring, with an NVIDIA HPC SDK installation playbook coming […]
First seen by Oriel on .
AI summary
NVIDIA is introducing a four-node DGX Spark HPC Developer Kit that brings local multi-node scientific computing, AI workloads, and agent workflows to researchers’ desks.
- Each of four GB10 Grace Blackwell nodes connects directly to two neighbors via NVIDIA ConnectX-7, avoiding a separate network switch.
- The cluster offers 512GB combined memory and 20TB of NVMe storage; NVFP4 supports local deployment of models up to 700B parameters across nodes.
- The forthcoming NVIDIA HPC SDK playbook will provide GPU-accelerated C, C++ and Fortran compilers, libraries, and MPI tools for testing before larger systems.
- Demonstrated workloads include LAMMPS with Kokkos, NAMD, and NIM microservices; community validation includes GROMACS, OpenFOAM, WRF, OpenFold3, and Boltz-2.
- Reported uses include 70-qubit, 975-gate simulations on one DGX Spark and 15x faster genomic results without cluster queues.
#dgx spark #hpc #scientific computing #ai models
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| NVIDIA Blog | https://blogs.nvidia.com/?p=100038 | https://blogs.nvidia.com/blog/dgx-spark-hpc-developer-kit-sc26/ Read discussion |