Hi
Have you maximized the device’s performance?
$ sudo nvpmodel -m 0
$ sudo jetson_clocks
You can find our benchmark table below.
VLM on Orin with VILA 1.5-3B is ~7fps.
Thanks.
Hi
Have you maximized the device’s performance?
$ sudo nvpmodel -m 0
$ sudo jetson_clocks
You can find our benchmark table below.
VLM on Orin with VILA 1.5-3B is ~7fps.
Thanks.
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Benchmarking VLM on Orin | 6 | 446 | March 2, 2026 | |
| Jetson nano 8G Run VLM Benchmark | 3 | 617 | March 5, 2025 | |
| Problem: slow LLM inference speed on Jetson AGX Orin 64GB | 1 | 1008 | April 8, 2025 | |
| LLM library recomendations for maximum token speeds | 11 | 1045 | March 16, 2026 | |
| Running llama3.3 or llama4 on Jetson AGX Orin Developer Kit (64 GB) | 7 | 1358 | May 12, 2025 | |
| LLaVA Live Demo | 7 | 312 | July 3, 2025 | |
| LLMs token/sec | 1 | 1323 | April 8, 2024 | |
| LLaMa 2 LLMs w/ NVIDIA Jetson and textgeneration-web-ui | 86 | 26899 | May 10, 2024 | |
| VLM on video running on NVIDIA Jetson | 6 | 1537 | November 3, 2023 | |
| The token speed of qwen 2.5 vl 3b model is very lower on Jeston AGX Orin | 2 | 707 | September 22, 2025 |