OlliteRT is an open-source Android app that runs large language models locally via Google's LiteRT runtime, exposing an OpenAI-compatible API over LAN for lightweight always-on tasks like RSS summarization and smart home automation, with monitoring, logging, and security features.
OlliteRT is an open-source Android app that transforms old phones into local LLM servers exposing OpenAI-compatible APIs, supporting models like Gemma 4 E2B and Qwen 2.5 1.5B with configurable hardware acceleration, monitoring, and Home Assistant integration, all running offline on 5-10W power.
Long‑term LLM agents suffer from ever‑slowing execution and context poisoning because they continuously append every observation, action, and reasoning step to the prompt, but the SKILL.state approach replaces this growing history with a compact mutable state, dramatically cutting token usage while boosting accuracy and robustness across diverse benchmarks.
Apple and the Hasso Plattner Institute evaluated over 200 multilingual inference training experiments across nine base models and eleven languages, finding that training with Chinese rewards incurs just a 1.1 percentage‑point loss versus English, while low‑resource languages can cause severe performance collapses in specific model‑language combos.
The article examines recent HuggingFace experiments comparing how different harnesses affect large and small AI models, revealing that complex harnesses like Codex excel on big models while lightweight harnesses perform better on smaller ones, and discusses why future agents will demand far more compute than current setups.
DeepSeek’s open‑source DSpark applies speculative decoding to its V4 Flash and Pro models, delivering 51%‑400% inference throughput gains that vary by task, while also supporting other models such as Gemma and Qwen, positioning it as a versatile, cross‑model acceleration solution.
Google’s open‑source DiffusionGemma model leverages a 26‑billion‑parameter Mixture‑of‑Experts architecture and discrete diffusion decoding to generate whole text blocks, achieving up to four times faster generation—over 1100 tokens/s on an NVIDIA H100 and 700 tokens/s on an RTX 5090—while activating only 3.8 billion parameters during inference.
PhoneClaw and PokeClaw are open‑source, on‑device AI agents for iOS and Android that run Gemma 4 locally, offering offline privacy, zero‑cost operation, and native tool calling through iOS APIs or Android Accessibility services.
Google’s AI Edge Gallery lets you run cutting‑edge large language models such as Gemma 4 entirely offline on Android or iOS devices, offering absolute privacy, zero‑latency responses, and a modular platform with agent skills, thinking mode, multimodal input, and a prompt‑lab for on‑device AI experimentation.
Google’s AI Edge Gallery lets developers run open‑source large language models such as Gemma 4 directly on Android devices without network connectivity, offering an integrated framework with agent skills, thinking mode visualizations, multimodal interaction, and a prompt lab, thereby addressing privacy, latency, and offline AI needs.
Learn how to transform any PDF—including scanned documents—into well‑structured Markdown using a local LLM (Gemma 3 via Ollama), Python, PyMuPDF and Pillow, without cloud APIs or API keys, by converting pages to images, prompting the model, and saving the output.
This guide shows how to quickly and cheaply deploy the open‑source Google Gemma large language model on Alibaba Cloud Function Compute GPU using the new idle‑billing mode, covering prerequisites, Docker image creation, function setup, idle reservation, testing, monitoring, and cost estimation.
Google has released the open‑source Gemma large language model in 2 B and 7 B parameter versions, claiming superior performance to Llama 2 and Mistral across 18 benchmarks, especially in math and code, while running on laptops, desktops, IoT and cloud devices.
Google has released the open‑source Gemma LLM series (2B and 7B parameters) built on Gemini‑style architecture, offering free, commercial‑ready models that run on notebooks, support JAX/PyTorch/TensorFlow, outperform many open‑source peers, and have quickly sparked extensive community testing and discussion.
Google’s newly released open‑source Gemma models let developers run powerful large‑language‑model workloads on notebooks, workstations, or cloud platforms, offering competitive performance, extensive tooling, and built‑in safety measures for responsible AI deployment.
Google has launched Gemma, an open‑source large language model available in 2B and 7B parameter versions, built on the same technology as Gemini, outperforming many existing models and capable of running on ordinary laptops, with a detailed technical report and quick‑start guide provided online.
