What we're seeing as the NVIDIA Grace Blackwell GB10 and DGX Spark move from keynote stages to desks — and what it means for everyone who wants to own their inference instead of renting it from a hyperscaler.
The global compute marketplace is open. If you own a GB10, you can now list it, set your own rate, and keep 85% of every session someone runs on it — while we handle billing, payouts, and the customer relationship. Here's how it works and why we built it.
Read the announcement →A petaflop of FP4 and 128GB of coherent memory on a desk you can carry. The Spark isn't a workstation — it's a category reset.
03Per-token cloud pricing looks cheap until you run the numbers at volume. What an owned GB10 actually costs per hour — and where the break-even sits.
04NVLink-C2C, a coherent CPU–GPU address space, and why "unified memory" is the spec that actually changes which models you can run.
05Project DIGITS became the DGX Spark, partners shipped their own GB10 systems, and the software stack caught up fast. A timeline.
06What it's actually like to serve Llama 3.3 70B from a single Grace Blackwell — context limits, tokens per second, and where it shines.
Quantization on Blackwell, multi-GB10 clustering, and provider playbooks. Subscribe from your dashboard to get them first.