Edge on-device inference
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | AI territory |
|---|---|
| Categories | 15 |
| Companies | 84 |
| Map changed | 2026-08-29 |
| Map | open the map |
Edge on-device inference is a territory of the AI industry on map of ai. In short: edge and on-device inference optimizes ai model execution on local hardware through quantization and compression, reducing latency and costs. The map lists 84 products and companies in 15 categories.
The map of edge on-device inference has 15 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.
on-device inference runtimes13 products and companies · its own article →
Software runtimes that execute machine learning models directly on edge devices without cloud connectivity, enabling privacy-preserving and low-latency AI inference. Used by mobile developers, IoT manufacturers, and enterprises deploying AI at the edge.
Open ground
Most runtimes still struggle with seamless model optimization and quantization workflows that automatically adapt to highly heterogeneous hardware capabilities across devices.
edge ai silicon & npus7 products and companies · its own article →
model compression & quantization tools6 products and companies · its own article →
small language models (slms)9 products and companies · its own article →
on-device vision & multimodal ai5 products and companies
Products and companies
edge inference deployment platforms6 products and companies
Platforms that enable machine learning model inference directly on edge devices without cloud dependency, used by IoT developers, mobile engineers, and embedded systems teams to deploy AI locally for low-latency real-time decisions.
on-device ai for mobile apps5 products and companies
On-device AI inference runs machine learning models directly on mobile devices without cloud connectivity, enabling low-latency, privacy-preserving AI experiences. Used by app developers, mobile OS providers, and enterprises handling sensitive data.
Products and companies
Papers, last 30 days
- Mobile AI Factory: Building Specialized Language Models for Your Mobile Device 2026-11-10
- Cross3DGS: Unified Vulkan-Based 3D Gaussian Splatting Training from Workstations to Mobile Devices 2026-11-17
- Tracking Ethological Behaviors of Broiler Chickens Through Computer Vision (YoloV11) Using an Android Mobile Device 2026-11-17
- FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices 2026-11-13
- Acoustic Respiratory Phase Detection on Mobile Devices 2026-11-12
on-device speech & asr5 products and companies
Products and companies
mcu & microcontroller tinyml5 products and companies
Products and companies: tensorflow lite micro, edge impulse, microai, stm32 ai (x-cube-ai), eloquent arduino ml.
edge ai chips and npus6 products and companies · its own article →
Edge AI chips and NPUs are processors designed to run inference workloads directly on device without cloud connectivity. Device manufacturers, mobile OEMs, automotive suppliers, and industrial equipment makers deploy them to enable local AI processing.
Products and companies: qualcomm, apple silicon, nvidia jetson, hailo, mediatek, google tensor.
small language models6 products and companies
Small language models optimized for inference on edge devices without cloud connectivity. Mobile developers, embedded systems engineers, and enterprise teams use them to run natural language tasks locally on phones, IoT devices, and servers.
Products and companies: gemma, phi, qwen, smollm, liquid ai, mistral.
Papers, last 30 days:edge deployment platforms4 products and companies · its own article →
Platforms that deploy and manage machine learning inference directly on edge devices without cloud connectivity. Enterprises, IoT device makers, and mobile app developers use these to run models locally on phones, embedded systems, and industrial equipment.
Products and companies: nexa ai, deeplite, qualcomm ai hub, roboflow.
Papers, last 30 days:on-device assistants4 products and companies
On-device assistants run conversational AI and task automation directly on consumer devices without cloud connectivity. Users include smartphone owners, laptop users, and smart device owners seeking privacy-preserving voice and text interactions.
Products and companies: gemini nano, galaxy ai, copilot+ pcs, gpt4all.
industrial edge vision3 products and companies
Industrial edge vision deploys computer vision models directly on factory equipment, robots, and IoT devices without sending images to cloud servers. Manufacturing plants, logistics operators, and inspection automation teams use it to detect defects, track parts, and monitor production lines in real time.
Products and companies: viso.ai, landing ai, plainsight.
edge ai developer sdks frameworks0 products and companies · its own article →
SDKs and frameworks that enable developers to build and deploy machine learning models directly on edge devices without cloud dependency. Mobile app developers, embedded systems engineers, and IoT device manufacturers use these tools to run inference locally on phones, tablets, microcontrollers, and industrial equipment.
See also
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.