NVIDIA Jetson 边缘部署推理模型：优化与性能提升指南
原标题：Frontier Reasoning Reaches the Edge: How to Deploy and Optimize Models on NVIDIA Jetson
AI 摘要
NVIDIA 技术博客介绍了如何在 Jetson 边缘设备上部署和优化推理模型，以 Nemotron 3.5 Lightning 和 Qwen3.8-27B 为例。文章指出，新一代紧凑型开放模型使边缘 AI 具备推理和智能体能力，并详细说明了 NVFP4 量化和投机解码如何提升推理性能。这些优化使模型能够在 Jetson 上本地运行，减少对数据中心的依赖，适用于车载助手、实时异常检测和机器人等场景。
正文节选
Running reasoning and agentic AI at the edge has been harder than it needs to be. Until recently, models capable of multi-step reasoning were too large to run locally on edge hardware. Developers building agents have had to route inference through a data center, adding network dependency, increasing costs, and exposing data that may need to stay on device. That constraint is lifting. Several model families released throughout the summer have collectively marked a turning point for edge AI. This