Mobile on-device ai chips
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | AI territory |
|---|---|
| Categories | 13 |
| Companies | 69 |
| Map changed | 2026-08-29 |
| Map | open the map |
Mobile on-device ai chips is a territory of the AI industry on map of ai. In short: mobile on-device ai chips execute machine learning inference directly on smartphones, tablets, and wearables without sending data to servers. The map lists 69 products and companies in 13 categories.
The map of mobile on-device ai chips has 13 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.
flagship mobile soc npu8 products and companies
Specialized neural processing units integrated into flagship smartphone processors for on-device AI inference and machine learning tasks. Used by smartphone manufacturers and end-users for real-time AI features without cloud dependency.
Open ground
Current NPUs remain bottlenecked by power efficiency and thermal constraints when running large language models, leaving a gap for enterprise-grade on-device generative AI.
mid-range on-device ai soc5 products and companies
Mobile AI processors designed to run machine learning models directly on smartphones and tablets without cloud connectivity. Used by smartphone manufacturers, app developers, and mobile device users seeking privacy-preserving AI features.
on-device llm inference runtime7 products and companies
Software runtimes that execute large language models directly on mobile devices without cloud connectivity, enabling private and low-latency AI inference. Used by app developers, device manufacturers, and enterprises requiring on-device AI capabilities.
on-device generative ai features6 products and companies
On-device generative AI features run machine learning models directly on mobile devices without cloud dependency, enabling private and low-latency AI experiences. Used by smartphone manufacturers, app developers, and consumers seeking offline AI capabilities.
wearable & iot edge ai chips5 products and companies
mobile ai benchmarking & mlops3 products and companies
Products and companies
on-chip ai memory architecture4 products and companies
On-chip AI memory architectures are specialized memory systems integrated into mobile processors that enable fast, efficient AI inference directly on devices without cloud connectivity. Used by smartphone makers, AR/VR device manufacturers, and edge computing companies seeking low-latency AI processing.
flagship phone socs with npu7 products and companies
Flagship smartphone system-on-chip processors that integrate neural processing units for on-device AI inference and computation. Device manufacturers like Apple, Qualcomm, Samsung, and MediaTek ship these in premium phones to run machine learning models locally.
Products and companies: qualcomm snapdragon, apple a-series, mediatek dimensity, samsung exynos, google tensor, huawei kirin, unisoc.
npu ip and licensable cores6 products and companies
NPU IP cores and licensable designs that chipmakers integrate into mobile processors to accelerate on-device AI workloads. Mobile SoC designers license these cores to add neural processing capabilities to their flagship and mid-range processors.
Products and companies: arm, cadence, synopsys, ceva, verisilicon, expedera.
on-device runtimes and sdks5 products and companies
Software runtimes and SDKs that enable AI model inference and execution directly on mobile devices without cloud connectivity. Mobile app developers, device manufacturers, and AI framework companies use these to deploy neural networks on smartphones and tablets.
Products and companies: tensorflow lite, core ml, executorch, onnx runtime, mlc llm.
on-device language models5 products and companies
Processors and chips designed to run large language models directly on mobile devices without cloud connectivity. Mobile phone manufacturers, app developers, and device users deploy these chips to enable local inference of language models.
Products and companies: gemini nano, phi, llama, gemma, liquid ai.
edge and tinyml accelerators5 products and companies
Specialized hardware accelerators and processors designed to run machine learning inference directly on mobile devices and edge devices without cloud connectivity. Device makers, app developers, and ML engineers use these chips to deploy neural networks locally on phones, tablets, and IoT hardware.
Products and companies: hailo, syntiant, google coral, nvidia jetson, ambiq.
on-device assistants and apps3 products and companies
Mobile on-device AI chips that run inference and ML workloads directly on smartphones and tablets without cloud connectivity. Mobile device manufacturers, app developers, and end users deploy these chips to execute neural networks locally.
Products and companies: galaxy ai, pixel ai, copilot+ pcs.
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.