Ai mobile on-device model runners
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | territory of the AI industry |
|---|---|
| Categories | 7 |
| Companies | 40 |
| Part of | neural networks |
| Map last changed | 2026-10-15 |
| Map | open the map |
Ai mobile on-device model runners is a territory of the AI industry on map of ai. In short: ai mobile on-device model runners execute neural networks directly on smartphones and tablets without network connectivity. The map lists 40 products and companies in 7 categories.
The map of ai mobile on-device model runners has 7 categories. Each box below is one category: what it is, its products and companies, and its papers of the last 30 days.
mobile inference runtimes10 products and companies · its own article →
Software frameworks and runtimes that execute machine learning models directly on mobile devices without cloud connectivity. Mobile app developers, on-device AI feature teams, and edge computing projects use these to run inference locally on phones and tablets.
Open ground
TensorFlow Lite, Core ML, and ONNX Runtime all support quantization and model optimization for mobile; none of them provides automatic hardware-agnostic performance parity guarantees across Android and iOS chipsets without manual tuning per device.
small on-device models6 products and companies · its own article →
Small neural network models optimized to run inference directly on mobile devices without cloud calls. Mobile app developers, device manufacturers, and end users running apps on phones and tablets use these to perform tasks like image recognition, text processing, and voice understanding locally.
npu silicon sdks4 products and companies
NPU silicon SDKs provide software development kits for neural processing units embedded in mobile SoCs, allowing developers to write and optimize code that runs on dedicated AI accelerators. Mobile device manufacturers, app developers, and chipmakers use these SDKs to deploy machine learning on phones without relying solely on CPU or GPU.
Products and companies
developer edge ai platforms5 products and companies
Developer platforms that run machine learning models directly on mobile devices without cloud calls. Mobile app developers, embedded systems engineers, and on-device ML teams use these to deploy inference at the edge.
Products and companies
os-level on-device ai4 products and companies
OS-level on-device AI refers to machine learning inference engines and neural network runtimes integrated into mobile operating systems that execute models locally on the device without cloud connectivity. Mobile developers and device manufacturers use these to run vision, NLP, and audio tasks directly on phones and tablets.
Products and companies
local llm chat apps7 products and companies
Local LLM chat apps run large language models directly on mobile devices without cloud connectivity, letting users have conversational AI interactions on their phones and tablets. Mobile developers, privacy-conscious users, and organizations with connectivity constraints use these apps.
Products and companies
on-device speech apps4 products and companies
On-device speech recognition and processing that runs locally on mobile devices without sending audio to cloud servers. Used by mobile app developers, accessibility tool makers, and device manufacturers who need real-time voice input, wake-word detection, or speech-to-text without network dependency.
Products and companies
This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong. Demo page.