NVIDIA Walks Through Deploying Nemotron 3.5 Lightning on DGX Spark for Agents
NVIDIA Developer · youtube · 2026-08-11
NVIDIA has released a technical walkthrough demonstrating how to deploy the Nemotron 3.5 Lightning model on DGX Spark for high-volume agentic workloads.
- Model Specs: Nemotron 3.5 Lightning is a 30B parameter MoE model with 3B active parameters, designed specifically as a fast execution model for always-on agent systems. It supports up to 1M tokens of context.
- Deployment: The tutorial covers deployment using vLLM and DSpark speculative decoding, connecting the model to agent harnesses like OpenCode.
- Performance: On a single DGX Spark, the setup can handle 16 concurrent agent tasks, generating over 500 tokens per second.
Related event: NVIDIA Unveils Nemotron 3.5 Lightning and NeMo Switchyard Router(55 posts)→
More from coding & agent
- Six-month prediction: hiring for generic agent harnesses built from scratch will cool — yi111 · 2026-10-16
- Omarchy ISO wouldn't boot on NVIDIA, so he had Claude patch it — indragie · 2026-10-16
- Dev uses Grok to clean up 3D printer firmware, catches it sneaking in nonsense code — yacineMTB · 2026-10-16
- A rude AI agent took 89% of a shared resource in 102-run multi-agent personality experiment — Brave-History-6502 · 2026-10-16
- Guardrails can make risky delegation work — but it takes a full-time team, says iandanforth — iandanforth · 2026-10-16
- What can you truly delegate? Only tasks with unambiguous, verifiable results — iandanforth · 2026-10-16