AI Briefing#on-device-ai
The latest AI and developer news about #on-device-ai, with the original source and a short summary.
The latest AI and developer news about #on-device-ai, with the original source and a short summary.
Google has released LiteRT-LM, its on-device LLM inference engine.
The Kanana model achieved superior performance with 11T tokens, half the amount of global targets, and Kakao is reviewing industry-academia collaborations including GPU resource support.
On Android, on-device AI automatically removes sensitive information and metadata.
A Chrome extension that runs Gemma 4 on-device inside the browser.
Google's Gemma 4 model supports on-device AI inference that runs on iPhone without an internet connection.
Parcae scales up recurrence to reach 1.3B Transformer-level performance with 770M parameters.
It compiles English function descriptions into 22MB neural programs that run locally on llama.cpp.
Gemma 4 runs on iPhone using the local GPU and supports offline inference.
Pocket LLM v1.3.0 released, supporting local LLM chat on Android.
Google has released Google AI Edge Gallery, an optimized app for running the Gemma 4 model on-device.
Google has launched 'Google AI Edge Gallery,' an official app that lets users run Gemma 4 models locally on iPhone.
Google has released Google AI Edge Gallery, an open-source app for running on-device generative AI.
Samsung achieved 97%+ accuracy and under 200ms latency across 7 languages with on-device subtitle spotting for TVs.
On-device Android face verification optimization improved latency by 37% and throughput by 530%.
Emotional expressiveness improved through DPO training and actor recording data, surpassing GPT-4o on Korean image-based benchmarks
IBM unveiled the ultra-compact Granite 4.0 Nano model series, optimized for on-device and edge environments.
AI21 has released Jamba Reasoning 3B, a 3B-class on-device open-source reasoning model.
Introduces methods for converting RedNote's 3B-parameter OCR model, dots.ocr, to Core ML and MLX to run on the Apple Neural Engine.
Google has released EmbeddingGemma, a 308M-scale multilingual embedding model optimized for on-device environments.
Upstage and LG Electronics have signed a memorandum of understanding (MoU) to implement on-device AI by embedding an SLM in LG gram laptops.
Upstage optimizes Solar Mini for Intel Core Ultra processors and integrates the WriteUp app to build an on-device AI environment.
Upstage and Polaris Office are developing the world's first on-device AI document solution.
Google's multimodal model Gemma 3n has been released through various open-source libraries.
Stability AI has partnered with Arm to unveil 'Stable Audio Open Small,' a lightweight audio generation model that can run on-device on smartphones and similar devices.