For the operating system, Spark is an ARM-based system that runs Nvidia. OS DGXan Ubuntu Linux-based operating system built specifically for GPU processing. It comes with Nvidia’s AI software stack preinstalled, including the company’s CUDA libraries and NIM microservices.
Prices for the DGX Spark start at $3,999. It may seem like a lot, but given the cost of high-end GPUs with ample video RAM like the RTX Pro 6000 (around $9,000) or AI server GPUs (like $25,000 for an entry-level H100), the DGX Spark may represent a much less expensive option overall, although it’s not as powerful.
In fact, according According to Register, the GB10 chip’s GPU computing performance is roughly equivalent to an RTX 5070. However, the 5070 is limited to 12GB of video memory, limiting the size of AI models that can run on such a system. With 128GB of unified memory, the DGX Spark can run much larger models, albeit at a slower speed than, say, an RTX 5090 (which typically comes with 24GB of RAM). For example, to run the largest 120 billion parameter version of OpenAI’s recent gpt-oss language model, you would need around 80GB of memory, which is much more than you can get on a consumer GPU.
A return to 2016
Nvidia founder and CEO Jensen Huang marked the occasion of the DGX Spark launch by personally handing over one of the first units to Elon Musk at SpaceX’s Starbase facility in Texas, echoing a similar delivery Huang did to Musk at OpenAI in 2016.
“In 2016, we built DGX-1 to give AI researchers their own supercomputer. I personally delivered the first system to Elon at a small startup called OpenAI, and from there came ChatGPT,” Huang said in a statement. “DGX-1 launched the era of AI supercomputers and unlocked the scaling laws that drive modern AI. With DGX Spark, we return to that mission.”
