René's URL Explorer Experiment


Title: Blazing fast on-device GenAI with LiteRT-LM - Google Developers Blog

Open Graph Title: Blazing fast on-device GenAI with LiteRT-LM

X Title: Google for Developers Blog - News about Web, Mobile, AI and Cloud

Description: Google AI Edge’s LiteRT-LM provides a production-proven, highly optimized infrastructure for running Gemma 4 across cross-platform mobile and edge environments. It actively unlocks the model's native multimodal and agentic features on-device by utilizing memory-efficient dynamic loading, Multi-Token Prediction for up to a 2.2x speedup, and advanced orchestration tools like Thinking Mode and Constrained Decoding. Furthermore, the engine is rapidly expanding its integration surfaces beyond Android, introducing new native Swift APIs for Apple ecosystems and WebGPU-accelerated JavaScript APIs for high-performance, serverless browser inference.

Mail addresses
name@example.com?subject=Check out this site&body=Check out {url}

direct link

Domain: googledevelopers.blogspot.com


Hey, it has json ld scripts:
  {
    "@context": "https://schema.org",
    "@type": "BreadcrumbList",
    "itemListElement": [{
      "@type": "ListItem",
      "position": 1,
      "name": "Google for Developers Blog",
      "item": "https://developers.googleblog.com/"
    },{
      "@type": "ListItem",
      "position": 2,
      "name": "Blazing fast on-device GenAI with LiteRT-LM",
      "item": "https://developers.googleblog.com/blazing-fast-on-device-genai-with-litert-lm/"
    }]
  }
  
    {
      "@context": "https://schema.org",
      "@type": "Article",
      "headline": "Blazing fast on-device GenAI with LiteRT-LM",
      "description": "Google AI Edge’s LiteRT-LM provides a production-proven, highly optimized infrastructure for running Gemma 4 across cross-platform mobile and edge environments. It actively unlocks the model's native multimodal and agentic features on-device by utilizing memory-efficient dynamic loading, Multi-Token Prediction for up to a 2.2x speedup, and advanced orchestration tools like Thinking Mode and Constrained Decoding. Furthermore, the engine is rapidly expanding its integration surfaces beyond Android, introducing new native Swift APIs for Apple ecosystems and WebGPU-accelerated JavaScript APIs for high-performance, serverless browser inference.",
      "image": "https://storage.googleapis.com/gweb-developer-goog-blog-assets/images/may2026_liteRT-LM_v2_2x.2e16d0ba.fill-800x400.png",
      "datePublished": "2026-05-19",
      "author": [
        
        
          { "@type": "Person", "name": "Tenghui Zhu", "url": "/search/?author=Tenghui+Zhu" },
        
          { "@type": "Person", "name": "Yu-hui Chen", "url": "/search/?author=Yu-hui+Chen" },
        
          { "@type": "Person", "name": "Ram Iyengar", "url": "/search/?author=Ram+Iyengar" }
        
        
      ]
    }
  

twitter:cardsummary_large_image
og:imagehttps://storage.googleapis.com/gweb-developer-goog-blog-assets/images/Gemini_Generated_Image_7r4n957r4n.2e16d0ba.fill-1200x600.jpg

Links:

https://developers.google.com/
Community/Events https://developers.google.com/community
Learn https://developers.google.com/solutions/catalog
Blog https://developers.googleblog.com
YouTube https://www.youtube.com/user/GoogleDevelopers
https://developers.google.com/
Community/Events https://developers.google.com/community
Learn https://developers.google.com/solutions/catalog
Blog https://developers.googleblog.com
YouTube https://www.youtube.com/user/GoogleDevelopers
Tenghui Zhuhttps://googledevelopers.blogspot.com/search/?author=Tenghui+Zhu
Yu-hui Chenhttps://googledevelopers.blogspot.com/search/?author=Yu-hui+Chen
Ram Iyengarhttps://googledevelopers.blogspot.com/search/?author=Ram+Iyengar
Facebook https://www.facebook.com/sharer/sharer.php?u={url}
Twitter https://twitter.com/intent/tweet?text={url}
LinkedIn https://www.linkedin.com/shareArticle?url={url}&mini=true
https://googledevelopers.blogspot.com/blazing-fast-on-device-genai-with-litert-lm/
LiteRT-LMhttps://www.google.com/url?q=https://developers.google.com/edge/litert-lm/overview&sa=D&source=docs&ust=1780592726212598&usg=AOvVaw3Gs8snW_i7Uj8-rlk_W8mF
LiteRThttps://developers.google.com/edge/litert
Chrome, ChromeOS, the Pixel Watchhttps://developers.googleblog.com/on-device-genai-in-chrome-chromebook-plus-and-pixel-watch-with-litert-lm/
Androidhttps://play.google.com/store/apps/details?id=com.google.ai.edge.gallery
iOShttps://apps.apple.com/us/app/google-ai-edge-gallery/id6749645337
agentic capabilitieshttps://developers.googleblog.com/bring-state-of-the-art-agentic-skills-to-the-edge-with-gemma-4/
XNNPACKhttps://github.com/google/xnnpack
MLDrifthttps://developers.googleblog.com/litert-maximum-performance-simplified/
LiteRThttps://ai.google.dev/edge/litert/overview
LiteRT-LMhttps://ai.google.dev/edge/litert-lm
Multi-Token Prediction (MTP)https://blog.google/innovation-and-ai/technology/developers-tools/multi-token-prediction-gemma-4/
LiteRThttps://developers.googleblog.com/litert-the-universal-framework-for-on-device-ai/
recently launchedhttps://blog.google/innovation-and-ai/technology/developers-tools/multi-token-prediction-gemma-4/
apphttps://github.com/google-ai-edge/gallery
E2Bhttps://huggingface.co/litert-community/gemma-4-E2B-it-litert-lm
E4Bhttps://huggingface.co/litert-community/gemma-4-E4B-it-litert-lm
Gemma4 Multi-Modality support on phones shown here using the Google AI Edge Gallery app. https://github.com/google-ai-edge/gallery
constrained decoding (CD)https://ai.google.dev/edge/litert-lm/cpp#constrained_decoding
introducedhttps://developers.googleblog.com/on-device-function-calling-in-google-ai-edge-gallery/
Kotlin/C++https://ai.google.dev/edge/litert-lm/android
Swift APIhttps://ai.google.dev/edge/litert-lm/swift
JavaScript APIhttps://ai.google.dev/edge/litert-lm/js
Swift APIhttps://ai.google.dev/edge/litert-lm/swift
JavaScript APIhttps://ai.google.dev/edge/litert-lm/js
web solutionhttps://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference/web_js
LiteRT-LM CLIhttps://ai.google.dev/edge/litert-lm/cli
AI Edge Galleryhttps://github.com/google-ai-edge/gallery
codehttps://github.com/google-ai-edge/LiteRT-LM
io.googlehttps://io.google/2026/?utm_source=blogpost&utm_medium=pr&utm_campaign=devblogs&utm_content=
Mobilehttps://googledevelopers.blogspot.com/search/?technology_categories=Mobile
Webhttps://googledevelopers.blogspot.com/search/?technology_categories=Web
AIhttps://googledevelopers.blogspot.com/search/?technology_categories=AI
Announcementshttps://googledevelopers.blogspot.com/search/?content_type_categories=Announcements
Industry Trendshttps://googledevelopers.blogspot.com/search/?content_type_categories=Industry+Trends
Explorehttps://googledevelopers.blogspot.com/search/?content_type_categories=Explore
Generative AIhttps://googledevelopers.blogspot.com/search/?tag=Generative AI
LLM runtimehttps://googledevelopers.blogspot.com/search/?tag=LLM runtime
LLMhttps://googledevelopers.blogspot.com/search/?tag=LLM
On-device Machine Learninghttps://googledevelopers.blogspot.com/search/?tag=On-device Machine Learning
LiteRT-LMhttps://googledevelopers.blogspot.com/search/?tag=LiteRT-LM
Gemmahttps://googledevelopers.blogspot.com/search/?tag=Gemma
muti-modalityhttps://googledevelopers.blogspot.com/search/?tag=muti-modality
LiteRThttps://googledevelopers.blogspot.com/search/?tag=LiteRT
https://googledevelopers.blogspot.com/announcing-genkit-middleware-intercept-extend-and-harden-your-agentic-apps/
https://googledevelopers.blogspot.com/an-important-update-transitioning-gemini-cli-to-antigravity-cli/
Mobile Web Announcements Learn Bringing Gemma 4 12B to your Laptop: Unlocking Local, Agentic Workflows with Google AI Edge JUNE 3, 2026 https://googledevelopers.blogspot.com/bringing-gemma-4-12b-to-your-laptop-unlocking-local-agentic-workflows-with-google-ai-edge/
AI Cloud Announcements Documentation Build reliable multi-agent applications with ADK Go 2.0. Discover our new graph-based workflow engine, built-in human-in-the-loop, and dynamic orchestration JUNE 30, 2026 https://googledevelopers.blogspot.com/announcing-adk-go-20/
AI Cloud How-To Guides Announcements Driving the Agent Quality Flywheel from Your Coding Agent JUNE 30, 2026 https://googledevelopers.blogspot.com/driving-the-agent-quality-flywheel-from-your-coding-agent/
Mobile Web Announcements Best Practices Enhance Security and Trust: New Session Metadata in Sign in with Google JUNE 16, 2026 https://googledevelopers.blogspot.com/enhance-security-and-trust-new-session-metadata-in-sign-in-with-google/
Blog https://googledevelopers.blogspot.com
Bluesky https://goo.gle/3FReQXN
Instagram https://goo.gle/googlefordevs
LinkedIn https://goo.gle/gdevs-li
X (Twitter) https://goo.gle/gdevs-tw
YouTube https://goo.gle/developers
Google Developer Program https://developers.google.com/program
Google Developer Groups https://developers.google.com/community/gdg
Google Developer Experts https://developers.google.com/community/experts
Accelerators https://developers.google.com/community/accelerators
Women Techmakers https://www.womentechmakers.com
Google Cloud & NVIDIA https://developers.google.com/community/nvidia
Google API Console https://console.developers.google.com
Google Cloud Platform Console https://console.cloud.google.com
Google Play Console https://play.google.com/apps/publish
Firebase Console https://console.firebase.google.com
Actions on Google Console https://console.actions.google.com
Cast SDK Developer Console https://cast.google.com/publish
Chrome Web Store Dashboard https://chrome.google.com/webstore/developer/dashboard
Google Home Developer Console https://console.home.google.com/
https://developers.google.com/
Android https://developer.android.com
Chrome https://developer.chrome.com/home
Firebase https://firebase.google.com
Google Cloud Platform https://cloud.google.com
All products https://developers.google.com/products
Terms https://developers.google.com/terms/site-terms
Privacy https://policies.google.com/privacy

Viewport: width=device-width, initial-scale=1


URLs of crawlers that visited me.