Loading video...

Video Failed to Load

Go Home

Discover how anyone can easily get started running their own LLMs with Google for Developers' Gemma 2 (2B) onboard Jetson Orin Nano. ➡️ ✨ Ideal for students, researchers, and enthusiasts -- it provides a small, lightweight device for learning about #generativeAI.

NVIDIAAIDev's profile picture

NVIDIA AI Developer

111,530 subscribers

28,748 views • 1 year ago •via X (Twitter)

EducationScience & TechnologyGaming#generativeAI
LIVE

Anya Rossi• Live Now

Private livecam show

5 Comments

Google for Developers's profile picture
Google for Developers1 year ago

Small, but faster than our morning coffee kicking in! ☕💥

Krish Dasgupta's profile picture
Krish Dasgupta1 year ago

@googledevs How about on these ? 😎

Latent Spacer's profile picture
Latent Spacer1 year ago

@googledevs Can you scrape YT videos with it?

Alex Noyser's profile picture
Alex Noyser1 year ago

@googledevs Please help Ollama fix the problem with running on Jetson devices. Support has been broken since version 0.1.38.

Joshua Anang's profile picture
Joshua Anang1 year ago

@googledevs Can I have one please? This is my startup.

Related Videos

What happens when you combine voice, vision, and reasoning on-device? 🤔 Gemma 4 + a vision-language agent (VLA) running on NVIDIA Jetson Orin Nano shows how compact hardware can now handle real-world AI tasks using today’s open models—no cloud required. Get started:
1:50

What happens when you combine voice, vision, and reasoning on-device? 🤔 Gemma 4 + a vision-language agent (VLA) running on NVIDIA Jetson Orin Nano shows how compact hardware can now handle real-world AI tasks using today’s open models—no cloud required. Get started:

NVIDIA Robotics

25,655 views • 2 months ago

Build edge AI applications with Google tools using Hybrid LLMs. Learn how to combine the on-device capabilities of Gemma and cloud-based Gemini models for optimal performance and privacy.
4:00

Build edge AI applications with Google tools using Hybrid LLMs. Learn how to combine the on-device capabilities of Gemma and cloud-based Gemini models for optimal performance and privacy.

Google AI Developers

15,365 views • 1 year ago

We're launching the Google Antigravity SDK in preview. Built for developers and researchers who want total programmatic control to customize and deploy on their own terms, it gives you the exact same agent harness optimized for Gemini, with the ultimate flexibility to run it wherever and however you want. Learn how to get started with the Antigravity SDK: 👇
1:11

We're launching the Google Antigravity SDK in preview. Built for developers and researchers who want total programmatic control to customize and deploy on their own terms, it gives you the exact same agent harness optimized for Gemini, with the ultimate flexibility to run it wherever and however you want. Learn how to get started with the Antigravity SDK: 👇

Google Antigravity

31,095 views • 1 month ago

If you’re considering a stereo camera for Jetson, I tested a ZED Mini Stereo camera. It’s about $400 (vs. $250 for Jetson Orin Nano), and Stereolabs says current lead time is 6 weeks. I ended up ordering from a third-party seller.
0:20

If you’re considering a stereo camera for Jetson, I tested a ZED Mini Stereo camera. It’s about $400 (vs. $250 for Jetson Orin Nano), and Stereolabs says current lead time is 6 weeks. I ended up ordering from a third-party seller.

Yu Xiang

92,801 views • 6 months ago

Gemma 4 running locally on a Nintendo Switch :) 1.5 tokens per second haha, but it runs! Google Gemma Google AI Developers Google DeepMind
2:57

Gemma 4 running locally on a Nintendo Switch :) 1.5 tokens per second haha, but it runs! Google Gemma Google AI Developers Google DeepMind

Maddie D. Reese

188,407 views • 3 months ago

The ultimate #BackToSchool supplies just dropped! 🎒Get ready for smarter learning with new tools in the Google Gemini! Discover Guided Learning, integrated visuals, and exam prep tools to help students build their knowledge. Learn more:
0:30

The ultimate #BackToSchool supplies just dropped! 🎒Get ready for smarter learning with new tools in the Google Gemini! Discover Guided Learning, integrated visuals, and exam prep tools to help students build their knowledge. Learn more:

Google for Education

28,982 views • 11 months ago

The Jetson Nano is designed specifically for AI: It can run AI language models locally - without needing cloud connections. Think of it like a Raspberry Pi specifically optimized for AI applications. This $249 device fundamentally changes how AI will develop:
0:42

The Jetson Nano is designed specifically for AI: It can run AI language models locally - without needing cloud connections. Think of it like a Raspberry Pi specifically optimized for AI applications. This $249 device fundamentally changes how AI will develop:

GC Cooke

126,208 views • 1 year ago

We (Luis Felipe Casas and I) handed out 21 NVIDIA #Jetson Orin Nano kits to students in my computer vision class this semester. All teams showcased their live Jetson-powered demos in the classroom at the end of the course! Here are a few sample projects👇 1. Hand gesture for control
0:38

We (Luis Felipe Casas and I) handed out 21 NVIDIA #Jetson Orin Nano kits to students in my computer vision class this semester. All teams showcased their live Jetson-powered demos in the classroom at the end of the course! Here are a few sample projects👇 1. Hand gesture for control

Yu Xiang

29,338 views • 2 months ago

Discover power beaming's potential to revolutionize energy distribution and device powering. This compendium offers insights for researchers and developers, establishing a common framework for analysis and future advancements. Quote WSTWTR35 for 35% off this title now!
0:43

Discover power beaming's potential to revolutionize energy distribution and device powering. This compendium offers insights for researchers and developers, establishing a common framework for analysis and future advancements. Quote WSTWTR35 for 35% off this title now!

World Scientific

320,733 views • 1 year ago

Jensen just unveiled the new NVIDIA Jetson Orin Nano Super, optimized for on-device AI processing in robots, boasting 70 trillion operations (INT8) per second, 102GB/s memory bandwidth, 25 watts power consumption, and a price of $249.
1:40

Jensen just unveiled the new NVIDIA Jetson Orin Nano Super, optimized for on-device AI processing in robots, boasting 70 trillion operations (INT8) per second, 102GB/s memory bandwidth, 25 watts power consumption, and a price of $249.

The Humanoid Hub

194,171 views • 1 year ago

We took our most efficient model and made an open-source iOS app📱but why? As phones get faster, more AI will happen on device. With OLMoE, researchers, developers, and users can get a feel for this future: fully private LLMs, available anytime. Learn more from Luca Soldaini 🎀👇
2:09

We took our most efficient model and made an open-source iOS app📱but why? As phones get faster, more AI will happen on device. With OLMoE, researchers, developers, and users can get a feel for this future: fully private LLMs, available anytime. Learn more from Luca Soldaini 🎀👇

Ai2

234,874 views • 1 year ago

How I discovered and exploited an Unauthenticated RCE in BYOB (Build Your Own Botnet), an open-source post-exploitation framework for students, researchers and developers with close to 9k stars on GitHub!
0:37

How I discovered and exploited an Unauthenticated RCE in BYOB (Build Your Own Botnet), an open-source post-exploitation framework for students, researchers and developers with close to 9k stars on GitHub!

chebuya

65,143 views • 1 year ago

Great games belong everywhere players are. 🌍✨ Google Play is a unified universe for your games. We're building a seamless experience for your players between mobile and PC, empowering creators to bring their worlds to massive new audiences. Discover how the industry's most innovative developers are using Google Play to turn great games into global, cross-device phenomenons: #GDC2026 #ReadytoPlay
1:00

Great games belong everywhere players are. 🌍✨ Google Play is a unified universe for your games. We're building a seamless experience for your players between mobile and PC, empowering creators to bring their worlds to massive new audiences. Discover how the industry's most innovative developers are using Google Play to turn great games into global, cross-device phenomenons: #GDC2026 #ReadytoPlay

Google Play business community

15,006 views • 4 months ago

We teamed up with Google for Developers to create a community partnership focused on using NVIDIA technologies on Google Cloud. With new learning pathways on generative AI, inference, and more — join to connect with developers and start learning 👉
0:36

We teamed up with Google for Developers to create a community partnership focused on using NVIDIA technologies on Google Cloud. With new learning pathways on generative AI, inference, and more — join to connect with developers and start learning 👉

NVIDIA AI Developer

13,032 views • 8 months ago

OMG… you can now fine-tune your own AI model and run it entirely on your device. No servers. No API keys. No data leaks. Gemma 3 270M just made local LLMs real and it only takes about an hour to build your own. Here’s how:
0:23

OMG… you can now fine-tune your own AI model and run it entirely on your device. No servers. No API keys. No data leaks. Gemma 3 270M just made local LLMs real and it only takes about an hour to build your own. Here’s how:

Louis Gleeson

79,508 views • 9 months ago

Android’s newest feature updates are designed to be made your own – the ideal ingredients for a device that's uniquely you 🤌✨ Discover the latest here:
1:05

Android’s newest feature updates are designed to be made your own – the ideal ingredients for a device that's uniquely you 🤌✨ Discover the latest here:

Android

47,222 views • 1 year ago

🚨 NVIDIA Introduces Jetson Nano Super > compact AI computer capable of 70-T operations per second > designed for robotics, it supports advanced models, including LLMs, and costs $249
1:14

🚨 NVIDIA Introduces Jetson Nano Super > compact AI computer capable of 70-T operations per second > designed for robotics, it supports advanced models, including LLMs, and costs $249

Haider.

3,424,541 views • 1 year ago

To build safer AI, we need to understand how models "think". 🧠 Enter Gemma Scope 2, a new set of tools to interpret Gemma 3: our family of lightweight open models. It can help researchers trace internal reasoning, debug complex behaviors and identify risks →
0:56

To build safer AI, we need to understand how models "think". 🧠 Enter Gemma Scope 2, a new set of tools to interpret Gemma 3: our family of lightweight open models. It can help researchers trace internal reasoning, debug complex behaviors and identify risks →

Google DeepMind

219,392 views • 6 months ago

Personalizing images in the Google Gemini just got easier — and you’re in total control. ✨ We’re introducing new ways for Personal Intelligence and Nano Banana 2 to generate images that can reflect your life, interests, and the things you care about most. Here’s how it works 🧵
1:25

Personalizing images in the Google Gemini just got easier — and you’re in total control. ✨ We’re introducing new ways for Personal Intelligence and Nano Banana 2 to generate images that can reflect your life, interests, and the things you care about most. Here’s how it works 🧵

Google

114,147 views • 2 months ago

See how Apple Distinguished Educator Dr. Helmi Norman used Memoji and augmented reality to make learning history more engaging for students. Get ideas for using video and animation with your own students in the Apple Education Community.
0:32

See how Apple Distinguished Educator Dr. Helmi Norman used Memoji and augmented reality to make learning history more engaging for students. Get ideas for using video and animation with your own students in the Apple Education Community.

Apple Education

7,322,011 views • 2 years ago