The Log · Field Notes from GB10 Studio

Notes from the
edge of compute.

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.

02

Why the DGX Spark is the most important desktop AI computer in a decade

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.

Hardware·May 21, 2026·7 min
03

GB10 vs. the cloud: the real economics of owning your inference

Per-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.

Economics·May 14, 2026·6 min
04

Grace Blackwell, explained: 128GB of unified memory and what it unlocks

NVLink-C2C, a coherent CPU–GPU address space, and why "unified memory" is the spec that actually changes which models you can run.

Deep Dive·May 7, 2026·8 min
05

From CES to your desk: the DGX Spark rollout and NVIDIA's ecosystem push

Project DIGITS became the DGX Spark, partners shipped their own GB10 systems, and the software stack caught up fast. A timeline.

Ecosystem·Apr 30, 2026·6 min
06

Running 70B models locally: real-world throughput on the GB10

What it's actually like to serve Llama 3.3 70B from a single Grace Blackwell — context limits, tokens per second, and where it shines.

Benchmarks·Apr 23, 2026·7 min

More in the pipeline

Quantization on Blackwell, multi-GB10 clustering, and provider playbooks. Subscribe from your dashboard to get them first.

Soon