TensorRT Edge-LLM Completes the MLPerf Edge Agentic Benchmark 6.4x Faster on Jetson AGX Thor

<img width="768" height="432" src="https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-768x432.png" class="webfeedsFeaturedVisual wp-post-image" alt="" style="display: block; margin-bottom: 5px; clear:both;max-width: 100%;" link_thumbnail="" decoding="async" srcset="https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-768x432.png 768w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-179x101.png 179w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-300x169.png 300w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-625x352.png 625w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-1536x864.png 1536w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-645x363.png 645w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-660x370.png 660w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-500x281.png 500w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-160x90.png 160w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-362x204.png 362w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-196x110.png 196w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-1024x576.png 1024w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-960x540.png 960w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6.webp 1920w" sizes="(max-width: 768px) 100vw, 768px" title="image5" />AI agents are moving from cloud data centers to vehicles, robots, and other edge devices. Unlike a chatbot that answers a single prompt, an agent works through...<img width="768" height="432" src="https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-768x432.png" class="webfeedsFeaturedVisual wp-post-image" alt="" style="display: block; margin-bottom: 5px; clear:both;max-width: 100%;" link_thumbnail="" decoding="async" loading="lazy" srcset="https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-768x432.png 768w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-179x101.png 179w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-300x169.png 300w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-625x352.png 625w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-1536x864.png 1536w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-645x363.png 645w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-660x370.png 660w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-500x281.png 500w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-160x90.png 160w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-362x204.png 362w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-196x110.png 196w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-1024x576.png 1024w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6-960x540.png 960w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/09/image5-6.webp 1920w" sizes="auto, (max-width: 768px) 100vw, 768px" title="image5" /><p>AI agents are moving from cloud data centers to vehicles, robots, and other edge devices. Unlike a chatbot that answers a single prompt, an agent works through a sequence of steps. It selects tools, evaluates their results, and continues reasoning within an increasingly long conversation. This workflow places new demands on edge inference. The model must generate tokens quickly…</p> <p><a href="https://developer.nvidia.com/blog/tensorrt-edge-llm-completes-the-mlperf-edge-agentic-benchmark-6-4x-faster-on-jetson-agx-thor/" rel="nofollow" data-wpel-link="internal" target="_self">Source</a></p>