On-device edge inference apis
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | territory of the AI industry |
|---|---|
| Categories | 11 |
| Companies | 69 |
| Map last changed | 2026-08-29 |
| Map | open the map |
On-device edge inference apis is a territory of the AI industry on map of ai. In short: apis and platforms that enable machine learning model inference directly on edge devices, mobile phones, and local servers without cloud dependencies. The map lists 69 products and companies in 11 categories.
The map of on-device edge inference apis has 11 categories. Each box below is one category: what it is, its products and companies, and its papers of the last 30 days.
mobile inference runtimes15 products and companies · its own article →
Software runtimes and frameworks that enable machine learning model inference directly on mobile devices and edge hardware without cloud connectivity. Used by mobile app developers, embedded systems engineers, and edge computing platforms seeking low-latency, privacy-preserving AI.
Open ground
A sharp gap remains in seamless cross-platform model optimization and deployment that automatically adapts quantization, pruning, and architecture selection based on device heterogeneity without requiring manual engineering per target hardware.
mobile npu silicon5 products and companies
Mobile NPU silicon refers to dedicated neural processing units integrated into smartphones and edge devices for on-device AI inference without cloud connectivity. Used by mobile app developers, device manufacturers, and enterprises needing low-latency, privacy-preserving AI.
Products and companies
edge ai accelerator hardware6 products and companies
Hardware accelerators that enable machine learning inference directly on edge devices without cloud connectivity, used by IoT manufacturers, mobile developers, and embedded systems engineers.
Products and companies
model optimization & quantization tools6 products and companies · its own article →
on-device llm sdks10 products and companies
On-device LLM SDKs enable developers to run large language models directly on edge devices without cloud connectivity, serving mobile apps, IoT devices, and privacy-conscious applications. Used by mobile developers, embedded systems engineers, and enterprises requiring offline AI capabilities.
on-device computer vision apis5 products and companies
APIs that enable machine learning inference directly on devices without cloud connectivity, used by mobile apps, embedded systems, and edge devices for real-time computer vision tasks.
Products and companies
on-device audio & speech inference4 products and companies
Products and companies
platform os ai apis4 products and companies
APIs that run machine learning inference on edge devices without sending data to servers. Mobile app developers, IoT device manufacturers, and embedded systems integrators use these to add AI features while keeping computation local.
Products and companies
browser and web inference5 products and companies
Browser and web inference APIs enable developers to run machine learning models directly in web browsers on client devices without server calls. Web developers, browser-based productivity apps, and real-time web applications use these APIs to perform tasks like image recognition, text processing, and speech inference locally.
Products and companies
edge deployment platforms6 products and companies · its own article →
On-device edge inference APIs enable developers to run machine learning models directly on client devices without server calls. Mobile app developers, embedded systems engineers, and IoT device makers use these APIs to perform inference locally.
Products and companies
Papers, last 30 days
on-device speech and vision sdks3 products and companies
SDKs that run speech recognition and computer vision models on user devices without cloud calls. Mobile app developers, edge device makers, and enterprises use them to process audio and images locally.
Products and companies
see alsoadjacent territories with an article
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.