DGX Spark 64GB

Headlines · 2

1. 1d
   Run Nemotron-3.5 Lightning on DGX Spark with TensorRT Edge-LLM

   An NVIDIA Technical Blog tutorial shows how to run the text-only Nemotron-3.5 Lightning model on a 64GB DGX Spark using TensorRT Edge-LLM. The trtedge command-line interface downloads the model and builds inference engines, while the workflow covers terminal chat testing and serving through a local OpenAI-compatible API. The tutorial also demonstrates optional DSpark speculative decoding, which uses a draft model to propose tokens for the main model to verify. NVIDIA reports higher mean generation speeds with DSpark on its SpeedBench 1K, SpeedBench 2K and HumanEval prompt workloads. The measurements used DGX OS 7.6.0, NVFP4, batch size one, one concurrent streaming request and a 128-token output limit.

   NVIDIA Technical Blog · 🔥 5
2. Oct 23
   Nvidia DGX Spark 64GB Arrives Oct. 23 at $4,999

   Nvidia’s new 64GB DGX Spark arrives Oct. 23 with a starting price of $4,999 and is available through manufacturing partners Acer, ASUS, Dell, Gigabyte, HP, and MSI. It retains the GB10 Grace Blackwell Superchip, DGX OS, and Nvidia’s AI software ecosystem, including Ollama, vLLM, PyTorch with CUDA, Nemotron models, and the Nvidia Agent Toolkit. Nvidia says the system supports models with up to 100 billion parameters, but TechRepublic notes that this vendor claim is not a guarantee for every model or workload. The 64GB configuration has not been independently benchmarked for the report, and its reduced memory may constrain model size, context length, and concurrent workloads. Buyers should confirm final configuration and regional pricing with the manufacturer.

   TechRepublic · 🔥 0

Experience and discussion from the community

Share my DGX Spark 64GB experienceAsk about DGX Spark 64GB