正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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

95,863 subscribers

11,841 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

5 条评论

Google AI Developers 的头像

Google AI Developers1 年前

✨ 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 的头像

Google AI Developers1 年前

Build live, interactive apps and sophisticated audio-centric experiences, including real-time speech transcription, translation, and rich voice-driven interactions ↓

Google AI Developers 的头像

Google AI Developers1 年前

We’re working to roll out full multimodal features, and are collaborating with partners to bring Gemma 3n to the open-source community in the coming weeks. Explore the model’s text and image capabilities in AI Edge, and text capabilities in Google AI Studio:

Rainmaker 的头像

Rainmaker2 年前

Here I share an XGBoost model that delivers a 25% CAGR with minimal drawdown on Visa stock. In this free Substack post I share code and commentary for a powerful Machine Learning strategy that delivers powerful returns.

David Fergus 的头像

David Fergus1 年前

I don't understand - I've installed both the 2B and 4B models on my phone, but it tells me it's just text-based?? I have no audio or video. I downloaded from the AI Studio Gallery, under AI Chat..

相关视频

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 次观看 • 1 年前

📲 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.

📲 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

16,628 次观看 • 1 年前

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 次观看 • 1 年前

NEW: Alibaba just released Qwen 3.5 Small — a family of powerful multimodal models available in a range of sizes (0.8B, 2B, 4B, and 9B parameters). Perfect for on-device applications! They can even run 100% locally in your browser on WebGPU, powered by Transformers.js! 🤯

NEW: Alibaba just released Qwen 3.5 Small — a family of powerful multimodal models available in a range of sizes (0.8B, 2B, 4B, and 9B parameters). Perfect for on-device applications! They can even run 100% locally in your browser on WebGPU, powered by Transformers.js! 🤯

Xenova

102,359 次观看 • 3 个月前

The next generation of mobile apps will run multimodal AI locally by default. Today, we’re making it practical for developers to ship. We just launched NexaSDK for Mobile on Product Hunt. Developers can run the latest multimodal AI models fully on-device in iOS & Android apps with Apple Neural Engine and Qualcomm Hexagon NPU acceleration. In just 3 lines of code, build chat, multimodal, search, and audio features with no cloud cost, complete privacy, 2x faster speed and 9× better energy efficiency. Try out NexaSDK for Mobile and we’d love your feedback (Product Hunt link in thread).

The next generation of mobile apps will run multimodal AI locally by default. Today, we’re making it practical for developers to ship. We just launched NexaSDK for Mobile on Product Hunt. Developers can run the latest multimodal AI models fully on-device in iOS & Android apps with Apple Neural Engine and Qualcomm Hexagon NPU acceleration. In just 3 lines of code, build chat, multimodal, search, and audio features with no cloud cost, complete privacy, 2x faster speed and 9× better energy efficiency. Try out NexaSDK for Mobile and we’d love your feedback (Product Hunt link in thread).

NEXA AI

319,337 次观看 • 5 个月前

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

723,883 次观看 • 2 个月前

Mini-Omni 2 understands image, audio and text inputs all via end-to-end voice conversations with users 🔥 > Understands and processes images, speech, and text > Generates real-time speech responses > Supports interruptions during speech Technical Overview: > Concatenates image, audio, and text features for input. > Uses text-guided delayed parallel output for real-time speech > Involves encoder adaptation, modal alignment, and multimodal fine-tuning Best part: MIT licensed ⚡

Mini-Omni 2 understands image, audio and text inputs all via end-to-end voice conversations with users 🔥 > Understands and processes images, speech, and text > Generates real-time speech responses > Supports interruptions during speech Technical Overview: > Concatenates image, audio, and text features for input. > Uses text-guided delayed parallel output for real-time speech > Involves encoder adaptation, modal alignment, and multimodal fine-tuning Best part: MIT licensed ⚡

Vaibhav (VB) Srivastav

45,409 次观看 • 1 年前

Super excited to introduce Gemma 4 12B! 💎 - Multimodal: audio, image, video, and text input - Novel architecture: we removed the multimodal encoders for a unified, streamlined arch - New MacOS desktop app powered by LiteRT - MTP support Excited to see what you build with it!

Super excited to introduce Gemma 4 12B! 💎 - Multimodal: audio, image, video, and text input - Novel architecture: we removed the multimodal encoders for a unified, streamlined arch - New MacOS desktop app powered by LiteRT - MTP support Excited to see what you build with it!

Omar Sanseviero

122,854 次观看 • 2 天前

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks

Adrien Grondin

109,700 次观看 • 7 个月前

LISA being the fastest kpop female soloist to reach 1B, 2B, 3B, 4B and 5B streams on spotify.

LISA being the fastest kpop female soloist to reach 1B, 2B, 3B, 4B and 5B streams on spotify.

่

37,374 次观看 • 2 个月前

✨ 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 次观看 • 1 年前

Stable Diffusion 3.5 from Stability AI is now LIVE on Civitai! Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. Generate with SD 3.5 Live on Civitai here👇🏽 All images used to create this video were generated with SD 3.5 by our community 🫶🏽

Stable Diffusion 3.5 from Stability AI is now LIVE on Civitai! Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. Generate with SD 3.5 Live on Civitai here👇🏽 All images used to create this video were generated with SD 3.5 by our community 🫶🏽

Civitai

31,210 次观看 • 1 年前

jina-embeddings-v5-omni is here! Our first universal embedding model for text, images, audio, and video. Available in two sizes: small (1.57B, 1024-dim, 32K context) and nano (0.95B, 768-dim, 8K context). Both support Matryoshka truncation down to 32 dimensions. v5-omni is back-compatible: if you already use jina-embeddings-v5-text-small/nano, the existing text indexes work with v5-omni out of the box. Without reindexing the text, just index your multimodal content with v5-omni and start searching images, audio, and video.

jina-embeddings-v5-omni is here! Our first universal embedding model for text, images, audio, and video. Available in two sizes: small (1.57B, 1024-dim, 32K context) and nano (0.95B, 768-dim, 8K context). Both support Matryoshka truncation down to 32 dimensions. v5-omni is back-compatible: if you already use jina-embeddings-v5-text-small/nano, the existing text indexes work with v5-omni out of the box. Without reindexing the text, just index your multimodal content with v5-omni and start searching images, audio, and video.

Jina AI

130,989 次观看 • 24 天前

1/5 MiniCPM-V 4.6 (1.3B) is now live 🚀🚀 High-res visual processing, optimized for consumer-grade and mobile hardware. We’ve leveraged the latest LLaVA-UHD v4 technique to cut vision encoding costs by 55%, enabling native edge deployment with extreme efficiency. 🔥 Beats Gemma4-E2B-it and Qwen3.5-0.8B across key multimodal and Artificial Analysis benchmarks — scoring higher than Qwen3.5-0.8B using just 2.5% of its token budget. ⚡ TTFT (75.7ms) 2.2x Faster than Qwen3.5-0.8B even with 3136² high-res images. 🏗️ ~1.5x Token Throughput compared with Qwen3.5-0.8B on a single RTX 4090. Try the model here: 🤗 Hugging Face: 💻 GitHub: 🔭 Modelscope: 🌐 Web Demo: 📱 App Demo:

1/5 MiniCPM-V 4.6 (1.3B) is now live 🚀🚀 High-res visual processing, optimized for consumer-grade and mobile hardware. We’ve leveraged the latest LLaVA-UHD v4 technique to cut vision encoding costs by 55%, enabling native edge deployment with extreme efficiency. 🔥 Beats Gemma4-E2B-it and Qwen3.5-0.8B across key multimodal and Artificial Analysis benchmarks — scoring higher than Qwen3.5-0.8B using just 2.5% of its token budget. ⚡ TTFT (75.7ms) 2.2x Faster than Qwen3.5-0.8B even with 3136² high-res images. 🏗️ ~1.5x Token Throughput compared with Qwen3.5-0.8B on a single RTX 4090. Try the model here: 🤗 Hugging Face: 💻 GitHub: 🔭 Modelscope: 🌐 Web Demo: 📱 App Demo:

OpenBMB

350,749 次观看 • 25 天前

I'm a bit confused... Google's Veo 2 is the best video model in text-to-video. But on the other hand... The newly released image-to-video for Veo 2 (on Freepik (now Magnific) and @FAL) feels underwhelming. Input images generated with Runway Frames. Here it is compared to Luma

I'm a bit confused... Google's Veo 2 is the best video model in text-to-video. But on the other hand... The newly released image-to-video for Veo 2 (on Freepik (now Magnific) and @FAL) feels underwhelming. Input images generated with Runway Frames. Here it is compared to Luma

Alex Patrascu

85,440 次观看 • 1 年前

Watch Gemma-4-E4B casually identify sea animals by classifying images in a single agentic session using its vision capabilities. (impressive for a 4B model 🚀) I'm convinced: the agents of tomorrow are local, free, fast, and run on every computer!

Watch Gemma-4-E4B casually identify sea animals by classifying images in a single agentic session using its vision capabilities. (impressive for a 4B model 🚀) I'm convinced: the agents of tomorrow are local, free, fast, and run on every computer!

Victor M

171,078 次观看 • 2 个月前

Llama 3.2 features 11B & 90B models, our first multimodal Llama models with support for vision tasks. These models can take in both image and text prompts to deeply understand and reason on inputs.

Llama 3.2 features 11B & 90B models, our first multimodal Llama models with support for vision tasks. These models can take in both image and text prompts to deeply understand and reason on inputs.

AI at Meta

121,502 次观看 • 1 年前

WHY IS NO ONE TALKING ABOUT THIS?? Gemma 3n model was one of the best surprises for me. The fact that you can run it on edge devices even with just 2GB of RAM is impressive. A few weeks back, I was on holiday and used the Gemini Live feature a lot. But I kept running into issues whenever I was in a place where the network wasn’t reliable. Gemma 3n : > Multimodal: Supports text and image inputs; video/audio in development. > Context Window: Up to 128K tokens (32K for 1B model). > Multilingual: Trained on 140+ languages. > Privacy: Offline, on-device processing for data security. > Model Sizes: E2B (5B parameters, 2GB RAM) and E4B (10–12B parameters, 3GB RAM). Video credit: Google YT

WHY IS NO ONE TALKING ABOUT THIS?? Gemma 3n model was one of the best surprises for me. The fact that you can run it on edge devices even with just 2GB of RAM is impressive. A few weeks back, I was on holiday and used the Gemini Live feature a lot. But I kept running into issues whenever I was in a place where the network wasn’t reliable. Gemma 3n : > Multimodal: Supports text and image inputs; video/audio in development. > Context Window: Up to 128K tokens (32K for 1B model). > Multilingual: Trained on 140+ languages. > Privacy: Offline, on-device processing for data security. > Model Sizes: E2B (5B parameters, 2GB RAM) and E4B (10–12B parameters, 3GB RAM). Video credit: Google YT

AshutoshShrivastava

210,455 次观看 • 1 年前

🚨 ELON: GROK WILL BE ABLE TO UNDERSTAND IMAGES, VIDEOS AND BEHAVIORS “It does, it actually does understand images at this point. It certainly is intended to work in sync. It's intended to be what's called a multimodal model, which means understanding text, images, video, and audio.” Peterson: “Okay, if it understands video, will it start to understand behavior?” Elon: “Yeah.” Source: DW

🚨 ELON: GROK WILL BE ABLE TO UNDERSTAND IMAGES, VIDEOS AND BEHAVIORS “It does, it actually does understand images at this point. It certainly is intended to work in sync. It's intended to be what's called a multimodal model, which means understanding text, images, video, and audio.” Peterson: “Okay, if it understands video, will it start to understand behavior?” Elon: “Yeah.” Source: DW

Mario Nawfal

58,182 次观看 • 1 年前

The QVAC SDK puts the "brain" directly into your pocket. From real-time on-device translation to multimodal understanding, build apps that work everywhere, even 30,000 feet in the air. Local AI is here: 💡Offline-First: No cloud, no latency, no "Department of Truth". 💻 Universal API: One codebase for iOS, Android, macOS, and Linux. 🔍 Multimodal: Understanding text, audio, and images without a server. If you can dream it, you can build it. The era of Stable Intelligence has begun. Start building:

The QVAC SDK puts the "brain" directly into your pocket. From real-time on-device translation to multimodal understanding, build apps that work everywhere, even 30,000 feet in the air. Local AI is here: 💡Offline-First: No cloud, no latency, no "Department of Truth". 💻 Universal API: One codebase for iOS, Android, macOS, and Linux. 🔍 Multimodal: Understanding text, audio, and images without a server. If you can dream it, you can build it. The era of Stable Intelligence has begun. Start building:

QVAC

36,352 次观看 • 1 个月前