NVIDIA releases Lightning model and smart routing

Summary

Developers building multi-agent systems can now skip manual routing logic and inference optimization—Switchyard handles cost/latency tradeoffs automatically across open, proprietary, and NVIDIA models. Lightning enables local deployment on RTX hardware, preserving privacy and infrastructure investment.

Why it matters

Developers building multi-agent systems can now skip manual routing logic and inference optimization—Switchyard handles cost/latency tradeoffs automatically across open, proprietary, and NVIDIA models. Lightning enables local deployment on RTX hardware, preserving privacy and infrastructure investment.

Sources

1. 1.up to 4x faster output speed, leading to 30% faster agentic task completion compared with other models in its class
2. 2.NeMo Switchyard maintains frontier-level accuracy while reducing task completion cost to nearly one-third of Opus 4.8 alone
3. 3.designed for this architecture. A frontier reasoning model such as Nemotron 3 Ultra or GPT-5.6 may plan and orchestrate a workflow, while smaller specialized models like Nemotron 3.5 Lightning can perform targeted tasks
4. 4.can run locally or on premises for high-volume, specialized tasks that require fast responses
5. 5.LangChain: achieved 74% lower cost in 145 multi-turn Deep Agents tasks by routing only 7% of calls to a frontier model