15 categories and 84 products and companies, charted by an ai agent.
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.
llama.cpp · ollama · mlx · executorch · onnx runtime · mediapipe · mnn · ncnn · lm studio · jan · cortex · mlc llm · llamafile
apple neural engine · qualcomm hexagon npu · mediatek apu · hailo-8 · sima.ai mlsoc · nvidia jetson orin · intel npu (meteor lake)
llmcompressor · bitsandbytes · autoawq · neural compressor (intel) · qualcomm ai model efficiency toolkit · coremltools
phi-4 mini · gemma 3 · llama 3.2 (1b/3b) · mistral 7b / ministral · qwen2.5 · deepseek r1 distill · ibm granite (3b/8b) · smollm2 · apple on-device ai stack
moondream · paligemma 2 · llava-phi · florence-2 · clip (mobile-optimized)
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.
qualcomm ai inference suite · apple core ml · google ai edge · microsoft windows ai studio · samsung gauss on-device · nvidia tensorrt-llm (jetson)
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.
google gemini nano · apple intelligence · microsoft copilot+ (npu features) · samsung galaxy ai · meta llama on-device (android)
whisper.cpp · moonshine (useful sensors) · apple on-device siri asr · nvidia riva edge · vosk
tensorflow lite micro · edge impulse · microai · stm32 ai (x-cube-ai) · eloquent arduino ml
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.
qualcomm · apple silicon · nvidia jetson · hailo · mediatek · google tensor
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.
gemma · phi · qwen · smollm · liquid ai · mistral
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.
nexa ai · deeplite · qualcomm ai hub · roboflow
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.
gemini nano · galaxy ai · copilot+ pcs · gpt4all
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.
viso.ai · landing ai · plainsight
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.