NVIDIA Jetson page: Thor vLLM Llama 3.1 8B, concurrency 8, 150.8 tok/s aggregate

NVIDIA Developer 'Jetson Benchmarks' page, Jetson AGX Thor Benchmarking Results table, read 2026-10-17. Jetson AGX Thor Developer Kit, JetPack 7.0, CUDA 13.0, TensorRT 10.13, vLLM (version not stated), input sequence length 2048, output sequence length 128. Weight dtype is not stated. The page gives no run count, no variance and no benchmark command, so confidence is below the MLPerf logs. Max concurrency 8 column: throughput with 8 requests in flight, so this is aggregate, not the per-request rate.

Vendor-measured. Weight quantization is not disclosed on the page, so format_id is left null rather than guessed. VLM rows from the same table were not filed.