jetson-examples

jetson

Discord

This repository provides examples for running AI models and applications on NVIDIA Jetson devices with a single command.

This repo builds upon the work of the jetson-containers, ultralytics and other excellent projects.

Features

  • 🚀 Easy Deployment: Deploy state-of-the-art AI models on Jetson devices in one line.
  • 🔄 Versatile Examples: Supports text generation, image generation, computer vision and so on.
  • ⚡ Optimized for Jetson: Leverages Nvidia Jetson hardware for efficient performance.

Install

To install the package, run:

pip3 install jetson-examples

Notes:

  • Check here for more installation methods
  • To upgrade to the latest version, use: pip3 install jetson-examples --upgrade.

Quickstart

To run and chat with LLaVA, execute:

reComputer run llava
jetson

Example list

Here are some examples that can be run:

Example Type Model/Data Size Docker Image Size Command Supported JetPack
🆕 reBot Arm Teleoperation Robotics / Teleoperation * JP6: 2.28GB archive; JP7.2: 7.71GB archive reComputer run rebot-arm-teleop 6.1, 6.2, 7.2
🆕 Ultralytics-yolo Computer Vision 15.4GB reComputer run ultralytics-yolo 4.6, 5.1.1, 5.1.2, 5.1.3, 6.0, 6.1, 6.2
🆕 YOLO11 Computer Vision * * reComputer run yolo11 5.1.1, 5.1.2, 5.1.3, 6.0, 6.1, 6.2, 6.2.1
🆕 YOLO26 Computer Vision * * reComputer run yolo26 5.1.1, 5.1.2, 5.1.3, 6.0, 6.1, 6.2, 6.2.1, 7.0, 7.1
🆕 YOLO26 TensorRT C++ (Native) Computer Vision ~30MB ONNX No Docker (native C++) reComputer run yolo26-tensorrt 6.0, 6.1, 6.2, 6.2.1, 7.0, 7.1, 7.2
🆕 Deep-Live-Cam Face-swapping 0.5GB 20GB reComputer run deep-live-cam 6.0
🆕 Live-VLM-WebUI Computer Vision (VLM) * * reComputer run live-vlm-webui 6.0, 6.1, 6.2, 6.2.1, 7.0, 7.1
🆕 LocateAnything Visual Grounding (VLM) 7.3GB 20.4GB reComputer run locateanything 6.2
🆕 llama-factory Finetune LLM 13.5GB reComputer run llama-factory 5.1.1, 5.1.2, 5.1.3
🆕 ComfyUI Computer Vision 20GB reComputer run comfyui 5.1.1, 5.1.2, 5.1.3
Depth-Anything-V2 Computer Vision 15GB reComputer run depth-anything-v2 5.1.1, 5.1.2, 5.1.3
Depth-Anything-V3 Computer Vision 7.6GB reComputer run depth-anything-v3 6.1, 6.2, 6.2.1
🆕 Gemma4 Text (LLM) 2.5GB 0.49GB reComputer run gemma4 6.1, 6.2, 6.2.1
🆕 Qwen3.5-4B Text (LLM) 2.5GB 0.2GB reComputer run qwen3.5-4b 6.1, 6.2, 6.2.1
🆕 Qwen3.6-35B Text (LLM) 28GB 0.59GB reComputer run qwen3.6-35b 6.1, 6.2, 6.2.1
🆕 Nemotron-3-Nano-30B Text (LLM) 24.5GB 0.59GB reComputer run nemotron-3-nano 6.1, 6.2, 6.2.1
Depth-Anything Computer Vision 12.9GB reComputer run depth-anything 5.1.1, 5.1.2, 5.1.3
Yolov10 Computer Vision 7.2M 5.74 GB reComputer run yolov10 5.1.1, 5.1.2, 5.1.3, 6.0
Llama3 Text (LLM) 4.9GB 10.5GB reComputer run llama3 5.1.1, 5.1.2, 5.1.3, 6.0
gpt-oss Text (LLM) 39GB 31.28GB reComputer run gpt-oss 6.1, 6.2, 6.2.1
🆕 GraspNet-Gemini Robotics / Grasping * 2.0GB reComputer run graspnet-gemini 6.0, 6.1, 6.2, 6.2.1
ros1-jp6 Robotics / ROS 1 * 1.27GB reComputer run ros1-jp6 6.1, 6.2, 6.2.1
nvblox Robotics / Mapping * 20.5GB+ reComputer run nvblox 6.x

Note: You should have enough space to run example, like LLaVA, at least 27.4GB totally

More Examples can be found examples.md

Calling Contributors Join Us!

How to work with us?

Want to add your own example? Check out the development guide.

We welcome contributions to improve jetson-examples! If you have an example you'd like to share, please submit a pull request. Thank you to all of our contributors! 🙏

This open call is listed in our Contributor Project. If this is your first time joining us, click here to learn how the project works. We follow the steps with:

  • Assignments: We offer a variety of assignments to enhance wiki content, each with a detailed description.
  • Submission: Contributors can submit their content via a Pull Request after completing the assignments.
  • Review: Maintainers will merge the submission and record the contributions.

Contributors receive a $250 cash bonus as a token of appreciation.

For any questions or further information, feel free to reach out via the GitHub issues page or contact edgeai@seeed.cc

TODO List

  • detect host environment and install what we need
  • all type jetson support checking list
  • try jetpack 6.0
  • check disk space enough or not before run
  • allow to setting some configs, such as BASE_PATH
  • support jetson-containers update
  • better table to show example's difference

👥 Contributors

License

This project is licensed under the MIT License.

Resources

Project links

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for seeed from gravatar.com seeed

Credits

Author: luozhixin

License

MIT License

Requires

Python >=3.8

Tags

llama llava gpt llm nvidia jetson multimodal jetson orin

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

jetson_examples-0.2.11.tar.gz (365.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

jetson_examples-0.2.11-py3-none-any.whl (468.2 kB view details)

Uploaded Python 3

File details

Details for the file jetson_examples-0.2.11.tar.gz.

File metadata

  • Download URL: jetson_examples-0.2.11.tar.gz
  • Upload date:
  • Size: 365.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.4

File hashes

Hashes for jetson_examples-0.2.11.tar.gz
Algorithm Hash digest
SHA256 56be86c3cdb4b22843a609915d27de6ded5c69d8f8db47ca2f7b8c835062a62a
MD5 8606a1f739096ab5b37556dc285e207e
BLAKE2b-256 de447c92669aa63e9950cfe49db15cc76f82c263eeb5973dd7a9933524a59928

See more details on using hashes here.

File details

Details for the file jetson_examples-0.2.11-py3-none-any.whl.

File metadata

File hashes

Hashes for jetson_examples-0.2.11-py3-none-any.whl
Algorithm Hash digest
SHA256 3cfc170794bf30f14f3f42d25e70b82dba1dd1c0c0bed1f2339f824335dabc29
MD5 8241fd559a9870acddc7cf790d18a98a
BLAKE2b-256 b58c796b412b5f520c37398f76e5444770fc5b670b56b97af9d1ce65bfeb90aa

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page