They arrived on a Saturday. Two NVIDIA DGX Spark units, picked up from the post office after sitting in customs for days. I'd been planning the setup for weeks — models pre-downloaded, Docker images queued, architecture docs written. I was ready.

What I wasn't ready for was this:

Two DGX Spark boxes on the kitchen counter
256GB of pooled Blackwell silicon, looking extremely patient.

The unboxing was satisfying. The hardware is beautiful — compact, dimpled metal chassis, surprisingly heavy for its size. The kind of thing that makes you feel like you're living in the future.

Unpacked DGX Spark with Quick Start Guide and power cord
Compact, clean, and ready to go. Almost.

And then I looked at the plug.

UK Type G plug on the DGX Spark power cord
Type G. Both of them.

Shipped from the UK, apparently — universal voltage (100–240V), but the wrong end for a US outlet. It was Saturday evening. Hardware stores were closed. I ordered NEMA 5-15 to IEC C5 cables from B&H Photo overnight, and the Sparks sat on the desk for two more days looking at me.

They powered on Monday morning.

What's running on them

Spark 1 is the always-on agent brain — Nemotron-3-Super-120B-A12B (NVFP4, ~80GB) via TRT-LLM, feeding the MetaClaw routing layer that decides what goes local vs. what escalates to Claude. Spark 2 handles async response scoring and eventually RL fine-tuning. 256GB pooled via NVLink-C2C for the big runs.

First real workload: OpenViking memory indexing. 713 items, 1.27M VLM tokens. The Sparks earned their keep on day one.

GTC keynote is Monday. Feels like good timing.

The plan

Two DGX Sparks. One UK plug problem. Fully resolved.

More soon.