Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

📲 Gemma 3n delivers advanced on-device AI with optimized performance and multimodal understanding. Take a closer look at the early preview text capabilities available in Google AI Studio, GenAI SDK, and text/image capabilities via MediaPipe.

Google AI Developers

112,996 subscribers

16,628 views • 1 year ago •via X (Twitter)

Science & Technology Gaming Education

Anya Rossi• Live Now

Private livecam show

9 Comments

Google AI Developers1 year ago

Check out the blog for more details ↓

ksminnovation1 year ago

AI is transforming healthcare! A KSM-led study shows AI can detect Celiac disease 4 years earlier @TalPatalon @MedPredict

Albert@PepinoCapital1 year ago

Related but can you add support for Google login (since it's a Google app?) so I'm logged in already when I try to download a model from @huggingface? Thank you

Sam Hocking1 year ago

No video/live video available yet. Seems really good!

Tsukuyomi1 year ago

on-device AI that gets smarter? sounds like a plot twist waiting to happen. let’s see how well it handles the chaos of reality.

Nicolas1 year ago

it does not seem to work with liteRT for web

KeySS Inc1 year ago

Sounds cool! Can't wait to see how this AI performs better than my coffee maker on a Monday morning.

Vishal1 year ago

On-device AI with multimodal skills is a smart move.

hamhamtar0xOwO1 year ago

@MirraTerminal good update

Related Videos

Let's go hands-on with #GeminiAI. Our newest AI model can reason across different types of inputs and outputs — like images and text. See Gemini's multimodal reasoning capabilities in action ↓

Let's go hands-on with #GeminiAI. Our newest AI model can reason across different types of inputs and outputs — like images and text. See Gemini's multimodal reasoning capabilities in action ↓

Google

1,005,688 views • 2 years 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.

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

✨ Introducing Gemma 3n, available in early preview today. The model uses a cutting-edge architecture optimized for mobile on-device usage. It brings multimodality, super fast inference, and more.

✨ Introducing Gemma 3n, available in early preview today. The model uses a cutting-edge architecture optimized for mobile on-device usage. It brings multimodality, super fast inference, and more.

Google AI Developers

125,209 views • 1 year ago

Key features include: -Expanded multimodal understanding with video and audio input, alongside text and images -Developer-friendly sizes: 4B and 2B (and many in between!) -Optimized on-device efficiency for 1.5x faster response on mobile compared to Gemma 3 4B

Key features include: -Expanded multimodal understanding with video and audio input, alongside text and images -Developer-friendly sizes: 4B and 2B (and many in between!) -Optimized on-device efficiency for 1.5x faster response on mobile compared to Gemma 3 4B

Google AI Developers

11,841 views • 1 year ago

Introducing Nano Banana Pro (Gemini 3 Pro Image), our new state-of-the-art image generation and editing model from Google DeepMind. It improves on the original model while adding new advanced capabilities, enhanced world knowledge and text rendering, allowing you to create and edit studio-quality, production-ready visuals.

Introducing Nano Banana Pro (Gemini 3 Pro Image), our new state-of-the-art image generation and editing model from Google DeepMind. It improves on the original model while adding new advanced capabilities, enhanced world knowledge and text rendering, allowing you to create and edit studio-quality, production-ready visuals.

Google

1,896,593 views • 6 months ago

Biggest news from Google I/O - Gemma 3n is out 🔥 > True multimodal - Audio, Image, Video AND Text in > Can be used in 4B and 2B sizes > Supports 140 languages > Even works on CPU w/ LiteRT (on Hugging Face) > Optimised for on-device 😍 BONUS: Coming to other open source libraries near you soon ;)

Biggest news from Google I/O - Gemma 3n is out 🔥 > True multimodal - Audio, Image, Video AND Text in > Can be used in 4B and 2B sizes > Supports 140 languages > Even works on CPU w/ LiteRT (on Hugging Face) > Optimised for on-device 😍 BONUS: Coming to other open source libraries near you soon ;)

Vaibhav (VB) Srivastav

62,751 views • 1 year ago

Friendly reminder that Google has an official app to run Gemma 4 on your phone. - 100% open source - Fully offline and private - Multimodal with text/audio/image - Works with Gemma E4B and E2B And the app is available on both iOS and Android. Steps and download below

Friendly reminder that Google has an official app to run Gemma 4 on your phone. - 100% open source - Fully offline and private - Multimodal with text/audio/image - Works with Gemma E4B and E2B And the app is available on both iOS and Android. Steps and download below

Paul Couvert

723,810 views • 2 months ago

At Google I/O, I sat down with Omar Sanseviero and 👩‍💻 Paige Bailey from Google DeepMind to talk about Gemma, open models, AI Studio, on-device AI, sovereign AI and the future of AI development. A great conversation on how building with AI is becoming more open, local and accessible.

At Google I/O, I sat down with Omar Sanseviero and 👩‍💻 Paige Bailey from Google DeepMind to talk about Gemma, open models, AI Studio, on-device AI, sovereign AI and the future of AI development. A great conversation on how building with AI is becoming more open, local and accessible.

Chubby♨️

13,514 views • 1 day ago

Introducing Veo 3.1 Lite, now available via the Gemini API and Google AI Studio. Veo 3.1 Lite supports both Text-to-Video and Image-to-Video, and is less than half the cost of Veo 3.1 Fast.

Introducing Veo 3.1 Lite, now available via the Gemini API and Google AI Studio. Veo 3.1 Lite supports both Text-to-Video and Image-to-Video, and is less than half the cost of Veo 3.1 Fast.

Google AI Developers

149,952 views • 2 months ago

Image captioning spots objects, but can it spot 𝘵𝘩𝘦 𝘷𝘪𝘣𝘦? 🤔 The "Caption This" demo in Google AI Studio showcases 2.5 Pro's upgraded creative capabilities and deep visual understanding to decode images and create contextual, witty captions.

Image captioning spots objects, but can it spot 𝘵𝘩𝘦 𝘷𝘪𝘣𝘦? 🤔 The "Caption This" demo in Google AI Studio showcases 2.5 Pro's upgraded creative capabilities and deep visual understanding to decode images and create contextual, witty captions.

Google AI Developers

96,545 views • 1 year ago

In this demo, you’ll see Gemini 3 Flash’s frontier-level reasoning and multimodal capabilities on display. The model is able to simultaneously conduct complex geometric calculations while processing complex inputs (video and image). You can play around with the slingshot in Google AI Studio here and share your favorite examples below:

In this demo, you’ll see Gemini 3 Flash’s frontier-level reasoning and multimodal capabilities on display. The model is able to simultaneously conduct complex geometric calculations while processing complex inputs (video and image). You can play around with the slingshot in Google AI Studio here and share your favorite examples below:

Google AI

55,411 views • 5 months ago

Learn how to build faster, leaner, and multimodal on-device apps with Gemma 3n in the #GoogleIO Developer Keynote with Gus (🤖🧠+🐍+🥑🗣️).

Learn how to build faster, leaner, and multimodal on-device apps with Gemma 3n in the #GoogleIO Developer Keynote with Gus (🤖🧠+🐍+🥑🗣️).

Google AI Developers

19,703 views • 1 year ago

🔥 Google Gemini 2.0 Flash is crazy good at pointing. I was over engineering before but now I'm just gonna bet on model capabilities. This is a demo of an AI cursor explaining a diagram on tldraw with just a prompt and an image. Streaming is also simple with Vercel AI SDK.

🔥 Google Gemini 2.0 Flash is crazy good at pointing. I was over engineering before but now I'm just gonna bet on model capabilities. This is a demo of an AI cursor explaining a diagram on tldraw with just a prompt and an image. Streaming is also simple with Vercel AI SDK.

Sriraam

186,978 views • 1 year ago

See Native Audio in action 🤠🦊 Our "Mumble Jumble" demo in Google AI Studio showcases the Live API's advanced voice capabilities: natural flow, distinct tone, emotion, and multilingual support.

See Native Audio in action 🤠🦊 Our "Mumble Jumble" demo in Google AI Studio showcases the Live API's advanced voice capabilities: natural flow, distinct tone, emotion, and multilingual support.

Google AI Developers

22,795 views • 1 year ago

Moro Hub holds the Guinness World Records title for the largest solar-powered data center. Powered by #Intel technology, it delivers optimized AI capabilities and energy-efficient performance. Learn more:

Moro Hub holds the Guinness World Records title for the largest solar-powered data center. Powered by #Intel technology, it delivers optimized AI capabilities and energy-efficient performance. Learn more:

Intel

15,766 views • 11 months ago

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,257 views • 8 months ago

Apple just released and open-sourced FastVLM! FastVLM is a lightning-fast vision-language model that combines rapid image and text understanding with efficient on-device performance. 100% Open Source

Apple just released and open-sourced FastVLM! FastVLM is a lightning-fast vision-language model that combines rapid image and text understanding with efficient on-device performance. 100% Open Source

Sumanth

43,685 views • 9 months ago

Introducing YouTube video 🎥 link support in Google AI Studio and the Gemini API. You can now directly pass in a YouTube video and the model can usage its native video understanding capabilities to use that, with just a link! 🚢

Introducing YouTube video 🎥 link support in Google AI Studio and the Gemini API. You can now directly pass in a YouTube video and the model can usage its native video understanding capabilities to use that, with just a link! 🚢

Logan Kilpatrick

792,105 views • 1 year ago