AI Prototyping on DGX Spark at Deschutes Tech Guild
On January 13, 2026, I am speaking at the Deschutes Tech Guild January Meetup in Bend, Oregon about AI prototyping on NVIDIA DGX Spark.
The talk is for developers who keep running into the same wall with local AI work: laptops throttle, cloud costs add up quickly, and the tooling can feel scattered. The session explores what changes when you put a small but serious AI machine on your desk and pair it with the NVIDIA ecosystem.
We will look at why the hardware architecture matters, how CUDA changes the shape of transformer inference and high-throughput embedding generation, and what benchmark results say about latency, throughput, and sustained load under proper batching.
The goal is simple: show how local inference can become a practical development superpower instead of a compromise.
Christian presenting AI Prototyping on DGX Spark at Deschutes Tech Guild.
Event
Deschutes Tech Guild - January Meetup
- When: January 13, 2026, 6:00 PM to 8:00 PM PST
- Where: EMBARK, 2843 NW Lolo Ave, Bend, OR
- Topic: AI Prototyping on DGX Spark
Slides
After the talk with the DGX Spark hardware.
Key Topics
- Local inference: Where local AI development helps and where it still has limits
- Hardware architecture: Why DGX Spark matters for developer workflows
- CUDA performance: Transformer inference and embedding generation in practice
- Benchmarking: Latency, throughput, batching, and sustained-load measurements
- Practical setup: Getting the NVIDIA ecosystem into a useful prototyping loop
About The Speaker
Christian has been building software since 2001, moving through the full stack from web and frontend work to large-scale backend and distributed systems. His recent exploration of DGX Spark is part of a broader effort to understand how modern AI and open source infrastructure fit together in practice.