# On-device AI Artificial intelligence and machine-learning inference performed locally on a user's device rather than in the cloud. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## CrowdStrike Accelerates Real-Time Data Classification with On-Device AI DevFeed: [CrowdStrike Accelerates Real-Time Data Classification with On-Device AI]() Original publisher: [Read original article]() Author: Lior Ribak Published: 2026-09-17T01:38:53.400452Z Content type: article Language: en Sources: [Blog]() Topics: [On-device AI](), [sensitive data](), [Language models](), [Endpoint security](), [Hardware](), [intel]() Tags: [data-security](), [endpoint-security](), [intel](), [language-models](), [npu](), [on-device-ai]() ### AI overview CrowdStrike and Intel introduced a Falcon Data Security capability that uses language models running on-device on dedicated AI hardware to classify sensitive data. The article explains that local inference is intended to avoid cloud latency and keep sensitive customer data on the endpoint while meeting real-time protection requirements. ### Source excerpt CrowdStrike worked closely with Intel to introduce a new capability in Falcon Data Security that classifies sensitive data using language models that run on-device using dedicated hardware for AI. Learn more! ## On-Device AI Series (Part 5): LiteRT-LM DevFeed: [On-Device AI Series (Part 5): LiteRT-LM]() Original publisher: [Read original article]() Author: Oğuzhan Aslan Published: 2026-09-14T05:59:12Z Content type: tutorial Language: en Sources: [ProAndroidDev - Medium]() Topics: [LiteRT](), [On-device AI](), [Large Language Model](), [Inference](), [Streaming](), [GPU](), [LLM evaluation / benchmarking](), [PyTorch]() Tags: [ai](), [android](), [android-development](), [benchmarking](), [gpu](), [inference](), [litert](), [llama](), [llm](), [multimodal](), [on-device](), [on-device-ai](), [programming](), [pytorch](), [qwen](), [software-development](), [streaming]() ### AI overview This tutorial explains LiteRT-LM for running large language models on-device. It covers the Engine/Session API, streaming output, system prompts, tool calling, multimodal inputs, thinking mode, and CPU-versus-GPU benchmarking. The article also discusses tradeoffs involving privacy, network independence, latency, memory, sampling configuration, and model capability compared with cloud APIs. ### Source excerpt Put your phone in airplane mode. Open the app, type a question, and watch the answer arrive one token at a time -- no spinner waiting on a network round-trip, no API key, no per-token bill, and nothing you typed ever leaving the device. LiteRT-LM removes the genuinely hard parts of running an LLM on-device -- KV-cache management, token streaming, backend selection -- but it doesn't remove your job so much as relocate it. What's left on your plate is a short, specific list: sizing a combined input+output token budget, owning your own sampling defaults, hand-building system prompts and tool calling out of raw text, and one native-library collision that presents as a SIGSEGV rather than a build error. Know those going in and the API itself is a clean three-step pattern. We'll get there in that order: Why you'd choose this runtime and what it costs you versus the cloud. The Engine/Session model you need to read the code at all. Real implementation samples -- streaming, system prompts and tool calling, multimodal inputs, thinking mode, and CPU-vs-GPU benchmarking. The anti-patterns to avoid. A developer-friendliness rating on the same rubric as Parts 1-4. Why Use LiteRT-LM? You reach for LiteRT-LM instead of hand-rolling generation on top of raw LiteRT when: You need multi-turn conversation, not single-shot inference -- session state and KV-cache bookkeeping are handled for you, and resetting a conversation is a session swap, not a model reload. You need streaming output -- token-by-token delivery for a responsive chat UI, instead of a blocking call that returns everything at once. You're choosing between CPU and GPU per device -- the explicit backend parameter turns that into a runtime decision instead of a build-time guess. You want a pre-converted model without doing your own PyTorch-to-LiteRT conversion work -- the Model Zoo covers Gemma, Qwen, Llama, and more out of the box. You're willing to own sampling -- the engine won't pick sane decoding defaults for you; that's on the ## Mastering Edge AI on Raspberry Pi with LiteRT and Gemma DevFeed: [Mastering Edge AI on Raspberry Pi with LiteRT and Gemma]() Original publisher: [Read original article]() Author: Lu Wang; Terry Heo; Naushir Patuck; José María Casanova Published: 2026-09-12T11:04:33.891311Z Content type: tutorial Language: en Sources: [Google Developers Blog]() Topics: [LiteRT](), [On-device AI](), [Local AI](), [AI, ML & Data Engineering](), [Google AI](), [cpu](), [Security, Privacy and Abuse Prevention]() Tags: [cli](), [cpu](), [edge](), [gemma](), [gpu](), [inference](), [litert](), [offline](), [on-device](), [real-time](), [robotics]() ### AI overview The article explains how to deploy Gemma models with LiteRT on a Raspberry Pi for local, real-time edge AI applications such as robotics. It highlights LiteRT-LM, CPU and GPU optimization, and reported performance figures for Gemma 4 E2B on Raspberry Pi 5. ### Source excerpt Deploying secure, real-time Edge AI on Raspberry Pi is now simplified using LiteRT and lightweight Gemma open models. LiteRT optimizes CPU and GPU performance, delivering fast token speeds for models like Gemma4, enabling real-time local reasoning for robotics. Developers can quickly convert, quantize, and run these models using the lightweight LiteRT CLI tool. Support for Hailo AI accelerators is also coming very soon. ## Dell Pro 14 Premium Review: A 2.55-Pound Magnesium Flagship With Tandem OLED DevFeed: [Dell Pro 14 Premium Review: A 2.55-Pound Magnesium Flagship With Tandem OLED]() Original publisher: [Read original article]() Author: Dylan Bryan Published: 2026-09-02T00:35:43Z Content type: article Language: en Sources: [StorageReview.com]() Topics: [dell](), [Security](), [cpu](), [intel](), [GPU](), [On-device AI]() Tags: [consumer](), [dell](), [display](), [enterprise](), [gpu](), [intel](), [memory](), [mobile](), [on-device-ai](), [review](), [security](), [storage](), [workstation]() ### AI overview This review examines the Dell Pro 14 Premium, a lightweight 14-inch commercial notebook designed for highly mobile professionals. It emphasizes portability, recycled magnesium construction, enterprise security and manageability, replaceable battery serviceability, Tandem OLED display quality, and on-device AI capabilities. Its integrated graphics and processor options are suited to office productivity and collaboration rather than GPU rendering or CAD workloads. ### Source excerpt The Dell Pro 14 Premium is what Dell calls its ultimate commercial notebook: a 14-inch, 2.54-pound magnesium flagship aimed at highly mobile professionals rather than workstation users. It sits above the Dell Pro and Dell Pro Plus lines, and the pitch is craftsmanship and portability with enterprise security and manageability underneath, not raw compute. The The post Dell Pro 14 Premium Review: A 2.55-Pound Magnesium Flagship With Tandem OLED appeared first on StorageReview.com. ## Running golf swing analysis on an Android device with a fine-tuned Gemma 4 model DevFeed: [Running golf swing analysis on an Android device with a fine-tuned Gemma 4 model]() Original publisher: [Read original article]() Published: 2026-08-29T23:00:00Z Content type: tutorial Language: en Sources: [John O'Reilly]() Topics: [Kotlin Multiplatform](), [gemma4](), [LiteRT](), [On-device AI](), [Fine-tuning]() Tags: [ai](), [android](), [cross-platform](), [fine-tuning](), [gemma](), [gemma-4](), [kotlin](), [kotlin-multiplatform](), [litert](), [model](), [multiplatform](), [on-device-ai]() ### AI overview This article explains how FormAI adds Android on-device golf-swing analysis using a small Gemma 4 model fine-tuned to imitate Gemini for a narrow coaching task. It covers generating training data with Gemini, fine-tuning with LoRA, converting the model for LiteRT-LM, and the current fallback to cloud analysis on other platforms. ### Source excerpt FormAI is a Kotlin Multiplatform app that analyses a video of your golf swing, basketball shot or running form and gives you coaching feedback. Up to now that has always meant uploading the video to Gemini and getting the response back over the network. We've added an option to do the golf swing analysis entirely on an Android device instead, using a small Gemma 4 model that we fine-tuned to imitate Gemini for that one task. LiteRT-LM, the runtime we use for this, is itself cross platform (Android, iOS, desktop and web), but we've only wired up the Android side so far, so this path lives in androidMain and the other targets report it as unavailable and fall back to the cloud. ## Engineering log: fine-tuning Gemma 4 E4B with LoRA to bring FormAI's coaching on-device DevFeed: [Engineering log: fine-tuning Gemma 4 E4B with LoRA to bring FormAI's coaching on-device]() Original publisher: [Read original article]() Published: 2026-08-28T23:00:00Z Content type: article Language: en Sources: [John O'Reilly]() Topics: [gemma4](), [Fine-tuning](), [lora](), [On-device AI](), [multiplatform](), [LiteRT](), [Android](), [Artificial Intelligence](), [API]() Tags: [ai](), [android](), [api](), [data](), [data-quality](), [engineering](), [fine-tuning](), [gemini](), [gemma](), [gemma-4](), [inference](), [kotlin-multiplatform](), [litert](), [lora](), [multiplatform](), [on-device]() ### AI overview This engineering log describes a prototype that distils FormAI's Gemini-based sports coaching feedback into Gemma 4 E4B fine-tuned with LoRA. The local pipeline uses seed videos, filters inadequate critiques, extracts frames, trains and merges the adapter, then converts the model to LiteRT-LM for possible on-device Android inference. ### Source excerpt ⚠ Note: this post is AI-generated. The text below was written by Claude, and documents findings from a series of Claude Code sessions working on this project -- the experiments, bugs and measurements described are ones that came out of those sessions. The engineering work is real and the numbers were measured rather than estimated, but the write-up is the model's own account of what it did, not a human's independent retelling of it. ## Meet editorial-guide-ramalama: An AI Assistant That Checks Your Fedora CommBlog and Magazine Articles Against Editorial Guidelines DevFeed: [Meet editorial-guide-ramalama: An AI Assistant That Checks Your Fedora CommBlog and Magazine Articles Against Editorial Guidelines]() Original publisher: [Read original article]() Author: Ananya Nalavathu Published: 2026-08-25T12:47:18Z Content type: article Language: en Sources: [Fedora Community Blog]() Topics: [Fedora](), [Retrieval Augmented Generation (RAG)](), [Artificial Intelligence](), [Local AI](), [Containers](), [Open Source](), [Tooling](), [On-device AI]() Tags: [ai](), [articles](), [blog](), [fedora-project-community](), [inference](), [local](), [mentored-projects](), [oci](), [open-source](), [rag](), [tool]() ### AI overview The article introduces editorial-guide-ramalama, a Retrieval-Augmented Generation assistant built for Fedora contributors. It checks drafts against Fedora's editorial guidelines and published articles, cites specific guidelines when it identifies problems, and suggests actionable fixes. The tool uses RamaLama to run open models locally as OCI containers, with built-in ingestion, chunking, and retrieval, avoiding API keys and external services. ### Source excerpt By Ananya Nalavathu and Francois Gonothi Toure Introduction Open source communities run on contribution, and contribution runs on documentation, storytelling, and knowledge sharing. At the Fedora Project, that means the Fedora Community Blog and Fedora Magazine, two publications that give contributors a voice and give the community a way to stay informed, inspired, and connected. [...] The post Meet editorial-guide-ramalama: An AI Assistant That Checks Your Fedora CommBlog and Magazine Articles Against Editorial Guidelines appeared first on Fedora Community Blog. ## Codename One Adds On-Device AI and Loopback MCP Support DevFeed: [Codename One Adds On-Device AI and Loopback MCP Support]() Original publisher: [Read original article]() Author: Shai Almog Published: 2026-08-02T00:00:00Z Content type: release Language: en Sources: [CodeName One]() Topics: [On-device AI](), [Model Context Protocol](), [Artificial Intelligence](), [LiteRT](), [Inference](), [Mobile](), [supply-chain-security]() Tags: [applications](), [inference](), [litert](), [mcp](), [mobile](), [on-device](), [on-device-ai](), [tensorflow-lite]() ### AI overview Codename One has added on-device vision, language, and LiteRT inference to its core, alongside a guarded loopback MCP transport for inspecting and operating applications. The article explains platform support, asynchronous OCR, model sessions, secure model downloads, and privacy limitations of local inference. ### Source excerpt Codename One now exposes on-device vision, language, and LiteRT inference in the core, while a guarded loopback MCP transport lets an LLM inspect and drive real applications. ## Build intelligent Android apps: On-device inference DevFeed: [Build intelligent Android apps: On-device inference]() Original publisher: [Read original article]() Author: Android Developers (noreply@blogger.com) Published: 2026-07-21T13:00:00Z Content type: article Language: en Sources: [Android Developers Blog]() Topics: [Android](), [On-device AI](), [ML Kit](), [Inference](), [gemma4](), [Google](), [Mobile]() Tags: [android](), [efficiency](), [features](), [gemini](), [gemma](), [gemma-4](), [google](), [inference](), [ml-kit](), [on-device](), [speed]() ### AI overview This Android developer article explains how to use Gemini Nano through ML Kit's Prompt API to build on-device features in the Jetpacker demo app. It covers itinerary summarization, expense management, and voice notes, emphasizing local processing, privacy, offline reliability, and avoiding cloud inference costs. The article reports that prompt iteration reduced response time from 13 seconds to under 2 seconds. ### Source excerpt Posted by Caren Chang, Developer Relations Engineer, Android Developer Relations Welcome back to the blog post series "Build intelligent Android apps" where we take a basic Android app and transform it into a personalized, intelligent, and agentic experience. In our previous post we introduced Jetpacker, the demo app we'll use throughout this series. In this blog post, we will share how you can use Gemini Nano through ML Kit's Prompt API to build intelligent on-device features. Building intelligent on-device features refers to the ability to process prompts and data directly on a device without sending data to a server. This offers a few advantages: User data can be processed locally on the device, preserving user privacy Functionality of the model is reliable even with spotty or no internet connection No additional cloud inference cost, since everything runs on the user's hardware With the benefits of on-device in mind, we identified three features to add in Jetpacker that can improve the user experience: summarizing trip itineraries, managing expenses, and capturing voice notes. On-device features in Jetpacker: Summarizing trip itineraries, managing expenses, and voice notes High quality tailored summarization of short texts The itinerary screen gives users a quick overview of all activities for a given trip. Since this screen contains a lot of information, it can quickly become overwhelming. To help users prepare without feeling overwhelmed, we can add a 'Get ready for your trip' section at the top. The romantic Paris trip is summarized as a classic Parisian adventure blending art, sights, and delicious food. A tip and some useful phrases are also added. By inputting a trip itinerary and asking an LLM to summarize it, we can generate a quick summary of the trip along with packing tips and useful local phrases. This is a great use case for an on-device model for several reasons: Performance and quality: Both the input and output text are relatively short. With tha ## Build intelligent Android apps: Introduction to Jetpacker DevFeed: [Build intelligent Android apps: Introduction to Jetpacker]() Original publisher: [Read original article]() Author: Android Developers (noreply@blogger.com) Published: 2026-07-21T13:00:00Z Content type: tutorial Language: en Sources: [Android Developers Blog]() Topics: [android-development](), [Mobile](), [On-device AI](), [Inference](), [genai](), [Open Source](), [App](), [ui](), [Google]() Tags: [android](), [android-development](), [apps](), [genai](), [google](), [inference](), [on-device](), [open-source](), [ui]() ### AI overview This introduction to a technical blog series presents Jetpacker, an open-source Android showcase app built for Google I/O. It outlines choices involving on-device, cloud, and hybrid inference, Android system integration, and agentic flows, with later posts promising implementation guidance and code examples. ### Source excerpt Posted by Jolanda Verhoef, Senior Developer Relations Engineer, Android Developer Relations Building GenAI features in your app usually means navigating through various models, APIs and architecture choices: Execution location: Where does your model run? On device, in the cloud, or both? Complexity: How complex is your setup? Are you doing a single inference call or do you need a more agentic flow? In-app or Android System: Should your feature be built into your Android app or does it fit better as an Android system integration? In this blog post series we'll navigate these choices with you. We will take you along on a journey, starting with a basic mobile app and transforming it into a personalized, intelligent, and agentic experience. Jetpacker: a demo travel app Jetpacker is a technical showcase app that our team built from the ground up for this year's Google I/O (built using Antigravity). At its core, Jetpacker helps users plan, explore, and enjoy their next big adventure. It shows an overview of your trips, the itinerary of each trip, and details of each event on that trip. Of course following all best practices of Android development, including a beautifully expressive Material UI design. And best of all? It's fully open source! Today we are publishing a series of technical blog posts diving deep into each of these features. We'll provide detailed implementation steps, code snippets, and architectural insights to help you build your own intelligent Android applications. On-device intelligence On-device features in Jetpacker: Summarizing trip itineraries, managing expenses, and voice notes Using an on-device model comes with no additional cloud inference costs, means you don't have to worry about internet connectivity, and lets users be confident that private information will be processed locally, on the device, without any of their data being sent to the cloud. In Jetpacker, we chose on-device inference for three of our features: The trip overview feature tra ## Accelerating Gemini Nano models on Pixel with frozen Multi-Token Prediction DevFeed: [Accelerating Gemini Nano models on Pixel with frozen Multi-Token Prediction]() Original publisher: [Read original article]() Published: 2026-06-26T18:30:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [AI Inference](), [On-device AI](), [Google](), [LLMs](), [gemma]() Tags: [ai](), [efficiency](), [energy](), [gemini](), [inference](), [machine-intelligence](), [mobile-systems](), [natural-language-processing](), [on-device](), [on-device-ai](), [phones]() ### AI overview Google Research describes a method for retrofitting Multi-Token Prediction onto frozen Gemini Nano v3 production models to accelerate on-device inference on Pixel phones. The approach targets mobile energy and memory constraints, improving the speed and energy efficiency of features such as notification summaries and proofreading without requiring separate drafting models. ### Source excerpt Machine Intelligence ## Use Your Mac for AI Agents: Self-Host Gemma 4 12 B with Pulumi and Tailscale DevFeed: [Use Your Mac for AI Agents: Self-Host Gemma 4 12 B with Pulumi and Tailscale]() Original publisher: [Read original article]() Author: Pablo Seibelt Published: 2026-06-04T00:00:00Z Content type: tutorial Language: en Sources: [Pulumi]() Topics: [gemma4](), [llama.cpp](), [Local AI](), [Infrastructure as code](), [macOS](), [On-device AI](), [multimodal]() Tags: [ai](), [download](), [gemma-4](), [gemma4](), [gpu](), [infrastructure-as-code](), [kubernetes](), [llama-cpp](), [macos](), [multimodal](), [python](), [tailscale](), [tutorials]() ### AI overview A tutorial for self-hosting Gemma 4 12 B on a modern Mac using llama.cpp with Apple Metal acceleration. It combines host-native inference with a local Kubernetes cluster, Pulumi infrastructure as code, and Tailscale for secure access, and reports validation results on a MacBook Pro with an Apple M3 Max and 36 GB RAM. ### Source excerpt If you run AI tools and agents, you've probably accepted three tradeoffs: your data leaves your network, you can't work offline, and your bill scales with usage. Open-weight models now run well on consumer hardware. Once the model is on your machine, your data stays local, inference works offline, and tokens cost nothing. If you own a modern Mac, you can run a high-quality model yourself. Gemma 4 is an open-weights model family from Google. This post focuses on Gemma 4 12 B, released in June 2026, using Unsloth's Q8_0 GGUF. The 12 B model fits comfortably on a modern Mac while leaving enough headroom for local llama.cpp and a chat UI. We'll use llama.cpp for host-native inference, k3d for a local Kubernetes cluster, Pulumi for infrastructure as code, and Tailscale for secure access. Prerequisites This setup was validated on the following hardware: macOS 26 Tahoe, version 26.5 MacBook Pro with Apple M3 Max 36 GB RAM On this machine, llama.cpp reported about 20 output tokens per second for a 160-token validation response with unsloth/gemma-4-12b-it-GGUF, gemma-4-12b-it-Q8_0.gguf, and a 131,072-token context. Sustained throughput varies by prompt length, thermal state, and llama.cpp settings. You'll need brew, docker, pulumi, and tailscale installed. We'll also install k3d during the process. Run Gemma 4 with host-native llama.cpp We use llama.cpp directly on macOS to leverage Apple Metal acceleration. Running the LLM on the host is more efficient than trying to pass GPU access into a local Kubernetes VM. Install the build tools: brew install cmake git Then build llama.cpp from source and download the multimodal projector. In validation, Homebrew llama.cpp 9430 could run text inference, but it could not load the new Gemma 4 12 B projector and failed with unknown projector type: gemma4uv. Building current llama.cpp from source fixed that. llm_home="$HOME/pulumi-gemma4-llm" mkdir -p "$llm_home/models" "$llm_home/logs" if [ ! -d "$llm_home/llama.cpp/.git" ]; then git clon ## Why I Think On-Device AI Changes Mobile Architecture DevFeed: [Why I Think On-Device AI Changes Mobile Architecture]() Original publisher: [Read original article]() Author: Akansha Jain Published: 2026-06-03T17:56:53Z Content type: opinion Language: en Sources: [Flutter Community - Medium]() Topics: [Artificial Intelligence](), [On-device AI](), [Mobile](), [Flutter](), [Android](), [data]() Tags: [ai](), [android](), [api](), [artificial-intelligence](), [dart](), [data](), [flutter](), [llm](), [mobile](), [on-device](), [on-device-ai]() ### AI overview This opinion article argues that on-device AI changes mobile application architecture by reducing dependence on network APIs. It discusses connectivity, per-call costs, and user-data concerns, drawing on a Flutter camera-demo crash involving a model already loaded on an Android phone. ### Source excerpt What a crashed app taught me about on-device AI -- and why I think you should care. I was building the demo I'd been planning for weeks. Flutter app running. Model loaded. Chat screen looking clean. I opened the camera -- the feature I was most excited about -- pointed it at something on my desk, and the app just crashed. Not a Dart exception. Not a red error screen. The whole thing just died. I stared at my Redmi Note 7 Pro for a second, opened it again, tried once more. Same result. Every single time I launched the camera with the model already loaded, Android killed my app. It took me longer than I'd like to admit to understand why. And when I finally did, I realised I'd been thinking about AI in mobile apps in a way that was quietly wrong for a long time. Before that, let me back up. For the past couple of years, whenever I wanted to add an AI feature to an app, the answer was pretty obvious: use an API. Need a chatbot? API. Need to analyze an image? API. Need text summarisation? API. A few lines of Dart, a request goes out, and something surprisingly intelligent comes back. It worked well enough that I stopped questioning the architecture behind it. Every one of those API calls travels over the network, gets processed on hardware you don't own, and comes back. Which means three things are always true, and always have been: The feature needs internet. Which is fine until you're in a metro tunnel, on a flight, or somewhere with patchy coverage. Your app just stops being smart. Users notice -- and they don't file bug reports, they just leave. You pay for every call. At low volume it's fine. At scale, it genuinely isn't. 10,000 users x 50 queries a day x per-token pricing. At low volume you barely notice it. At scale, those costs become a product decision. User data leaves the device. The health app where someone is logging symptoms. The finance app where they're describing their expenses. The journal app where they're writing things they wouldn't say out loud. For tho ## Expanding on-device AI in Microsoft Edge: New models and APIs for the web DevFeed: [Expanding on-device AI in Microsoft Edge: New models and APIs for the web]() Original publisher: [Read original article]() Author: Patrick Brosset Published: 2026-06-02T16:28:06Z Content type: article Language: en Sources: [Microsoft Edge Blog]() Topics: [Edge](), [On-device AI](), [Artificial Intelligence](), [API](), [Language models](), [Web](), [JavaScript](), [Microsoft](), [Cloud](), [Open Source](), [cpu](), [hugging face]() Tags: [ai](), [ai-apis](), [api](), [availability](), [cloud](), [cpu](), [github](), [gpu](), [javascript](), [microsoft-edge](), [models](), [on-device-ai](), [open-source](), [web](), [web-apis](), [web-platform]() ### AI overview Microsoft Edge is expanding its on-device AI capabilities with a developer preview of the smaller Aion-1.0-Instruct language model, new Language Detector and Translator APIs in Edge 148, and experimental on-device speech recognition through the Web Speech API. The updates target broader device support, including CPU-only systems, while emphasizing privacy, network independence, and web-developer experimentation. ### Source excerpt At Build 2025, we introduced the Prompt and Writing Assistance APIs in Microsoft Edge with the Phi-4-mini language model. Since then, we' The post Expanding on-device AI in Microsoft Edge: New models and APIs for the web appeared first on Microsoft Edge Blog. ## Holo3.1: Fast & Local Computer Use Agents DevFeed: [Holo3.1: Fast & Local Computer Use Agents]() Original publisher: [Read original article]() Author: Maxime Langevin; Hamza Benchekroun; Axel Moyal; Emrick Sinitambirivoutin; Antonio Loison; Avshalom Manevich; Tony Wu; Pierre-Louis Cedoz; Aurélien Lac; Ronan Riochet Published: 2026-06-02T14:13:23Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [computer-use](), [On-device AI](), [Local AI](), [Deployment](), [model-deployment](), [qwen](), [Benchmark](), [Cloud](), [NVFP4](), [browser]() Tags: [agent](), [agents](), [benchmark](), [benchmarks](), [browser](), [cloud](), [computer-use](), [deployment](), [devices](), [inference](), [json](), [model](), [models](), [nvfp4](), [on-device](), [performance](), [qwen](), [software]() ### AI overview Holo3.1 is a family of computer-use models designed to operate across web, desktop, and mobile environments and integrate with different agent frameworks. The release adds quantized checkpoints for local inference, native function-calling support, and model sizes ranging from 0.8B to 35B-A3B, targeting private, cost-effective, and high-performance deployments. ### Source excerpt Users want to run the same computer-use capabilities across desktop and mobile environments, with seamless integration with different agent frameworks. They want deployment flexibility, from cloud inference to fully local execution on end-user devices. This is why we are releasing the Holo3.1 family. Holo3.1 improves robustness across the three dimensions that matter most in production: environments (web, desktop, mobile), agent frameworks, and deployment targets. ## Private analytics via zero-trust aggregation DevFeed: [Private analytics via zero-trust aggregation]() Original publisher: [Read original article]() Published: 2026-05-27T16:56:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Security, Privacy and Abuse Prevention](), [Security](), [Zero Trust](), [Google](), [On-device AI](), [Artificial Intelligence](), [Android]() Tags: [ai](), [android](), [cryptographic](), [on-device-ai](), [privacy](), [security](), [security-privacy-and-abuse-prevention](), [zero-trust]() ### AI overview Google Research introduces a private analytics solution that combines cryptographic secure aggregation with the transparency and attestation properties of trusted execution environments. The design follows a zero-trust principle so Google can obtain only anonymized, aggregated population insights while individual user data remains protected. The article discusses applications of federated analytics and on-device technologies, including Android SafetyCore, Pixel Recorder, and Gboard. ### Source excerpt Security, Privacy and Abuse Prevention ## What's New in Android Security and Privacy in 2026 DevFeed: [What's New in Android Security and Privacy in 2026]() Original publisher: [Read original article]() Author: Eugene Liderman Published: 2026-05-12T17:00:00Z Content type: article Language: en Sources: [Security]() Topics: [Android](), [Android Security](), [Security](), [spoofing](), [Social engineering](), [threat detection](), [On-device AI](), [Chrome]() Tags: [ai](), [android](), [android-security](), [fraud](), [none](), [on-device-ai](), [security](), [social-engineering](), [spoofing](), [threat-detection]() ### AI overview The article describes planned Android security and privacy enhancements for 2026, including verified financial calls to combat spoofed banking scams. Android can verify incoming calls through participating financial apps and automatically end calls that are not genuine. It also highlights expanded Live Threat Detection, which uses on-device AI to analyze app behavior and warn about suspicious activity. ### Source excerpt New Android security and privacy features ## Gesture Recognition Based on TFLite DevFeed: [Gesture Recognition Based on TFLite]() Original publisher: [Read original article]() Author: John Lee Published: 2026-04-10T00:00:00Z Content type: tutorial Language: en Sources: [Blog on Developer Portal]() Topics: [TensorFlow Lite](), [Espressif](), [model-deployment](), [Tensorflow](), [Keras](), [On-device AI]() Tags: [ai](), [blog](), [deep-learning](), [deployment](), [development-board](), [edge-ai](), [edge-computing](), [esp-idf](), [espressif](), [how-to](), [inference](), [keras](), [model-deployment](), [model-training](), [tensorflow-lite]() ### AI overview This tutorial demonstrates gesture recognition on Espressif SoCs using TensorFlow Lite Micro. It covers data collection, model training, conversion for TFLite Micro, and deployment with C++ code for model loading, preprocessing, and inference. ### Source excerpt This article demonstrates how to implement gesture recognition using TensorFlow Lite Micro on Espressif SoCs. It covers the complete workflow from data collection and model training to model deployment, showcasing TensorFlow Lite Micro's applications in edge AI. ## AI application topologies: cloud, edge, local, and hybrid inference DevFeed: [AI application topologies: cloud, edge, local, and hybrid inference]() Original publisher: [Read original article]() Author: Alex Ewerlöf Published: 2025-10-24T21:15:00Z Content type: article Language: en Sources: [Alex Ewerlof Notes]() Topics: [Artificial Intelligence](), [Cloud](), [Local AI](), [Inference](), [On-device AI](), [Latency](), [Software as a service]() Tags: [ai](), [cloud](), [edge](), [edge-ai](), [inference](), [latency](), [local-ai](), [on-device-ai](), [privacy](), [saas]() ### AI overview The article categorizes AI application topologies by where inference compute occurs relative to data: cloud, edge, local, and hybrid. It describes trade-offs involving capability, latency, cost, privacy, connectivity, vendor limits, and centralized-service outages. ### Source excerpt Cloud AI, Edge AI, Local AI, and Hybrid AI ## Smart photo organization through privacy-first, on-device AI DevFeed: [Smart photo organization through privacy-first, on-device AI]() Original publisher: [Read original article]() Author: Cynthia Wang Published: 2025-10-15T08:00:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [On-device AI](), [Firebase](), [PWA](), [SDKs](), [web applications](), [browser]() Tags: [ai](), [ai-logic](), [firebase](), [gemini](), [hybrid-inference](), [on-device](), [on-device-ai](), [privacy](), [pwa](), [sdks](), [tutorials](), [web](), [web-browser]() ### AI overview This Firebase tutorial explains how to build a privacy-focused photo organization progressive web app using on-device AI. It describes running a local model in the browser so photos remain on the user's device and can be analyzed offline, with Firebase AI Logic SDKs detecting and caching compatible models such as Gemini Nano and providing a fallback approach for other browsers. ### Source excerpt News, tutorials, and updates from the Firebase team. ## Introducing: Local Browser AI DevFeed: [Introducing: Local Browser AI]() Original publisher: [Read original article]() Author: Alex Ewerlöf Published: 2025-10-13T07:51:29Z Content type: article Language: en Sources: [Alex Ewerlof Notes]() Topics: [browser](), [Artificial Intelligence](), [Browser Extension](), [JavaScript](), [On-device AI]() Tags: [ai](), [browser](), [extension](), [interface](), [javascript](), [on-device-ai](), [open-source]() ### AI overview This technical post explains how the Prompt API enables local language-model chat in the browser and examines the Local Browser AI extension, which is built with plain JavaScript and native browser APIs. It also describes the extension's permissions, privacy properties, open-source MIT license, and supported platforms. ### Source excerpt Using the new Prompt API for local chat in the browser ## New Firebase AI Logic features to explore - September 2025 updates DevFeed: [New Firebase AI Logic features to explore - September 2025 updates]() Original publisher: [Read original article]() Author: Miguel Ramos; Rachel Saunders Published: 2025-09-10T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Artificial Intelligence](), [SDKs](), [On-device AI](), [Image](), [API](), [Web](), [Android](), [Flutter](), [Unity](), [Chrome]() Tags: [ai](), [ai-logic](), [android](), [api](), [app-check](), [debug](), [firebase](), [firebase-ai-logic](), [flutter](), [gemini](), [hybrid-inference](), [image](), [images](), [inference](), [js](), [news](), [observability](), [offline](), [on-device](), [on-device-ai](), [unity](), [updates]() ### AI overview Firebase AI Logic's September 2025 updates add Gemini Live API voice interactions, client-side image editing and generation with Imagen, Nano Banana image workflows, hybrid on-device inference for web apps, and additional monitoring and observability capabilities. ### Source excerpt News, tutorials, and updates from the Firebase team. ## What's new in TensorFlow 2.20 DevFeed: [What's new in TensorFlow 2.20]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2025-08-19T16:00:00Z Content type: news Language: en Sources: [The TensorFlow Blog]() Topics: [LiteRT](), [On-device AI](), [Inference](), [Latency](), [IO](), [GPU](), [data](), [Google](), [Cloud](), [Python](), [C++](), [Kotlin]() Tags: [announcement](), [c-plus-plus](), [data](), [google](), [gpu](), [inference](), [io](), [kotlin](), [latency](), [litert](), [npu](), [on-device](), [python](), [tensorflow](), [tensorflow-core](), [tensorflow-lite]() ### AI overview TensorFlow 2.20 introduces the independent LiteRT repository as the future home for on-device inference, replacing the deprecated tf.lite module. LiteRT adds Kotlin and C++ APIs, improves NPU and GPU acceleration, and supports lower-latency inference with fewer memory copies. The release also adds tf.data input-pipeline warm-up controls and makes Google Cloud Storage support optional. ### Source excerpt Posted by the TensorFlow team TensorFlow 2.20 has been released! For ongoing updates related to the multi-backend Keras, please note that all news and releases, starting with Keras 3.0, are now published directly on keras.io. You can find a complete list of all changes in the full release notes on GitHub. tf.lite is being replaced by LiteRT The tf.lite module will be deprecated with development for on-device inference moving to a new, independent repository: LiteRT. The new APIs are available in Kotlin and C++. This code base will decouple from the TensorFlow repository and tf.lite will be removed from future TensorFlow Python packages, so we encourage migration of projects to LiteRT to receive the latest updates. More details to follow. As announced at Google I/O '25, LiteRT improves upon TFLite, particularly for NPU and GPU hardware acceleration and performance for on-device ML and AI applications. LiteRT provides a unified interface for Neural Processing Units (NPUs), removing the need to navigate vendor-specific compilers or libraries. This approach avoids many device-specific complications, boosts performance for real-time and large-model inference, and minimizes memory copies through zero-copy hardware buffer usage. For more information on the new repository and to sign up for the NPU Early Access Program, please reach out to the team at g.co/ai/LiteRT-NPU-EAP. Faster input pipeline warm-up with tf.data To help reduce latency, especially the time it takes for your model to process the first element of a dataset, we've added autotune.min_parallelism in tf.data.Options. This new option allows asynchronous dataset operations like .map and .batch to immediately start with a specified minimum level of parallelism, speeding up the initial warm-up time for your input pipelines. Changes to I/O GCS filesystem package The tensorflow-io-gcs-filesystem package for Google Cloud Storage support is now optional. Previously, it was installed, by default, with TensorFlow. If y ## Introducing hybrid on-device inference using Firebase AI Logic DevFeed: [Introducing hybrid on-device inference using Firebase AI Logic]() Original publisher: [Read original article]() Author: Siddharth Gupta; Erik Eldridge Published: 2025-06-09T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [On-device AI](), [Inference](), [AI Models](), [Web]() Tags: [ai](), [ai-logic](), [experimental](), [feature](), [firebase](), [gemini](), [hybrid-inference](), [inference](), [javascript](), [model](), [on-device](), [on-device-ai](), [web]() ### AI overview Firebase introduces an experimental hybrid inference feature in its AI Logic client SDK for Web. The feature uses available on-device models such as Gemini Nano in Chrome and falls back to cloud-hosted Gemini models when needed, supporting online and offline AI features. ### Source excerpt News, tutorials, and updates from the Firebase team. [Next page]()