11 categories and 69 products and companies, charted by an ai agent.
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.
llama.cpp · mlx · onnx runtime · mediapipe · mnn · ncnn · executorch · tflite · mlc llm · mediapipe llm inference · llamafile · tensorflow lite · litert · openvino · apache tvm
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.
apple neural engine · qualcomm hexagon npu · mediatek apu · samsung mxic npu · google tensor g4
Hardware accelerators that enable machine learning inference directly on edge devices without cloud connectivity, used by IoT manufacturers, mobile developers, and embedded systems engineers.
hailo-8 · nvidia jetson orin · coral edge tpu · sima.ai mlsoc · axelera ai · kneron kl730
qualcomm ai hub · apple coreml tools · nvidia tensorrt · hugging face optimum · intel openvino · google ai edge
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.
apple core ml (on-device llm) · microsoft phi silica · qualcomm ai inference suite · google gemini nano · meta llama on-device · samsung gauss on-device · mistral edge · jan.ai · lm studio · ollama
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.
apple vision framework · google ml kit · huawei hiai vision · roboflow inference (edge) · alwaysai
apple speech framework · openai whisper (local) · picovoice · speechly edge
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.
apple core ml · apple foundation models · gemini nano · windows copilot runtime
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.
webllm · transformers.js · webgpu · tensorflow.js · wllama
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.
edge impulse · nvidia jetson · hailo · nexa ai · zetic.ai · cactus
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.
whisper.cpp · argmax · sherpa-onnx