13 categories and 69 products and companies, charted by an ai agent.
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.
apple a18 pro neural engine · apple a19 pro neural engine · qualcomm snapdragon 8 elite · qualcomm snapdragon 8 gen 4 · mediatek dimensity 9400+ · samsung exynos 2500 npu · google tensor g5 · huawei kirin 9010 npu
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.
qualcomm snapdragon 7s gen 3 · mediatek dimensity 8300 · mediatek helio g100 · unisoc t820 · samsung exynos 1580
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.
qualcomm ai hub · apple core ml · google ml kit · samsung neural processing sdk · mediatek neuron sdk · llama.cpp mobile · mnn (alibaba mobile neural network)
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.
apple intelligence · google gemini nano · samsung galaxy ai · microsoft phi-3 mini (on-device) · xiaomi hyperai · oppo ai ernie on device
apple s10 (apple watch) · qualcomm snapdragon w5+ gen 2 · mediatek mt2625 iot npu · nordic semiconductor nrf9151 · ambiq apollo5
mlcommons mlperf mobile · ai benchmark (etri) · qualcomm snpe profiler
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.
lpddr5x with pim (samsung) · apple unified memory (a-series) · micron lpddr5x ai-optimized · sk hynix aim (ai-in-memory)
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.
qualcomm snapdragon · apple a-series · mediatek dimensity · samsung exynos · google tensor · huawei kirin · unisoc
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.
arm · cadence · synopsys · ceva · verisilicon · expedera
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.
tensorflow lite · core ml · executorch · onnx runtime · mlc llm
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.
gemini nano · phi · llama · gemma · liquid ai
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.
hailo · syntiant · google coral · nvidia jetson · ambiq
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.
galaxy ai · pixel ai · copilot+ pcs