BLAST RADIUS

Agents and harnesses · Quantization efficiency

TensorRT Edge-LLM Posts Jetson Benchmark Gain

Sep 16, 2026, first seen via NVIDIA technical blog

NVIDIA reported that TensorRT Edge-LLM completed the MLPerf Edge Agentic benchmark 6.4 times faster on Jetson AGX Thor.

Read the original at developer.nvidia.comOpens the publisher's site in a new tab

More in Agents and harnesses