EdgeAIDirectory

TensorFlow Lite

Google's lightweight inference framework for mobile and embedded — cross-platform model deployment for on-device AI.

TensorFlow Lite — Google's lightweight inference framework for mobile and embedded — cross-platform model deployment for on-device AI. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the inference frameworks segment with a focused feature set. Buyers researching inference frameworks options will find TensorFlow Lite a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Inference Frameworks ⭐ 195,309 stars tflite mobile embedded google

Ollama

The easiest way to run open-source LLMs locally — Docker-style model management for local AI inference.

Ollama — The easiest way to run open-source LLMs locally — Docker-style model management for local AI inference. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the local llm segment with a focused feature set. Buyers researching local llm options will find Ollama a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Local Llm ⭐ 172,661 stars llm local easy-setup docker-like

llama.cpp

Pure C/C++ LLM inference with GGUF quantization — run large language models on CPU and consumer GPUs.

llama.cpp — Pure C/C++ LLM inference with GGUF quantization — run large language models on CPU and consumer GPUs. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the local llm segment with a focused feature set. Buyers researching local llm options will find llama.cpp a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Local Llm ⭐ 113,819 stars llm cpp quantization cpu-inference

LocalAI

Free, open-source alternative to OpenAI APIs running locally — supports LLaMA, Whisper, Stable Diffusion, and more.

LocalAI — Free, open-source alternative to OpenAI APIs running locally — supports LLaMA, Whisper, Stable Diffusion, and more. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the local llm segment with a focused feature set. Buyers researching local llm options will find LocalAI a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Local Llm ⭐ 46,546 stars llm local open-source openai-compatible

Jan.ai

Open-source alternative to ChatGPT that runs offline — cross-platform desktop app for private local AI inference.

Jan.ai — Open-source alternative to ChatGPT that runs offline — cross-platform desktop app for private local AI inference. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the local llm segment with a focused feature set. Buyers researching local llm options will find Jan.ai a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Local Llm ⭐ 42,734 stars llm local open-source gui

ONNX Runtime

Microsoft's cross-platform inference engine — runs ONNX models on CPU, GPU, and specialized accelerators.

ONNX Runtime — Microsoft's cross-platform inference engine — runs ONNX models on CPU, GPU, and specialized accelerators. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the inference frameworks segment with a focused feature set. Buyers researching inference frameworks options will find ONNX Runtime a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Inference Frameworks ⭐ 20,677 stars onnx microsoft cross-platform open-source

Intel OpenVINO

Intel's open-source toolkit for optimizing and deploying deep learning inference across Intel hardware.

Intel OpenVINO — Intel's open-source toolkit for optimizing and deploying deep learning inference across Intel hardware. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the inference frameworks segment with a focused feature set. Buyers researching inference frameworks options will find Intel OpenVINO a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Inference Frameworks ⭐ 10,297 stars intel open-source inference optimization

Edge Impulse

End-to-end TinyML platform for IoT and embedded devices — model training, optimization, and deployment to MCUs.

Edge Impulse — End-to-end TinyML platform for IoT and embedded devices — model training, optimization, and deployment to MCUs. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the inference frameworks segment with a focused feature set. Buyers researching inference frameworks options will find Edge Impulse a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Inference Frameworks ⭐ 19 stars iot mcu edge tinyml

Apple Core ML

Apple's framework for running ML models on-device — hardware-accelerated via Neural Engine on iPhone, iPad, and Mac.

Apple Core ML — Apple's framework for running ML models on-device — hardware-accelerated via Neural Engine on iPhone, iPad, and Mac. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the mobile ai segment with a focused feature set. Buyers researching mobile ai options will find Apple Core ML a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Mobile Ai apple ios macos on-device

Arm ML

Arm's ML platform and Ethos NPU IP — the AI compute backbone of most mobile and IoT chips.

Arm ML — Arm's ML platform and Ethos NPU IP — the AI compute backbone of most mobile and IoT chips. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the edge hardware segment with a focused feature set. Buyers researching edge hardware options will find Arm ML a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Edge Hardware arm npu embedded ethos

Axelera AI

European edge AI chip startup — Metis AI Platform using phase-change memory for ultra-efficient inference.

Axelera AI — European edge AI chip startup — Metis AI Platform using phase-change memory for ultra-efficient inference. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the edge hardware segment with a focused feature set. Buyers researching edge hardware options will find Axelera AI a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Edge Hardware ai-chip edge pcm european

Cortex

Local AI inference server — run multiple LLMs locally with an OpenAI-compatible API for app development.

Cortex — Local AI inference server — run multiple LLMs locally with an OpenAI-compatible API for app development. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the local llm segment with a focused feature set. Buyers researching local llm options will find Cortex a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Local Llm llm local api open-source

Google Coral

Google's Edge TPU hardware — USB and M.2 accelerators for running TensorFlow Lite models at the edge with low power.

Google Coral — Google's Edge TPU hardware — USB and M.2 accelerators for running TensorFlow Lite models at the edge with low power. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the edge hardware segment with a focused feature set. Buyers researching edge hardware options will find Google Coral a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Edge Hardware tpu embedded google tflite

Hailo

Hailo AI processors for edge devices — high-performance inference chips for smart cameras and embedded vision.

Hailo — Hailo AI processors for edge devices — high-performance inference chips for smart cameras and embedded vision. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the edge hardware segment with a focused feature set. Buyers researching edge hardware options will find Hailo a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Edge Hardware ai-chip edge vision video-analytics

Kneron

Edge AI chip and solution provider — KL series NPUs for smart cameras, IoT devices, and embedded systems.

Kneron — Edge AI chip and solution provider — KL series NPUs for smart cameras, IoT devices, and embedded systems. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the edge hardware segment with a focused feature set. Buyers researching edge hardware options will find Kneron a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Edge Hardware ai-chip edge vision iot

LM Studio

Desktop app for running open-source LLMs locally — GUI for model discovery, download, and inference.

LM Studio — Desktop app for running open-source LLMs locally — GUI for model discovery, download, and inference. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the local llm segment with a focused feature set. Buyers researching local llm options will find LM Studio a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Local Llm llm local gui mac-windows

NVIDIA Jetson

NVIDIA's embedded computing platform for AI at the edge — Jetson Orin and Nano for robotics, vision, and autonomous systems.

NVIDIA Jetson — NVIDIA's embedded computing platform for AI at the edge — Jetson Orin and Nano for robotics, vision, and autonomous systems. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the edge hardware segment with a focused feature set. Buyers researching edge hardware options will find NVIDIA Jetson a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Edge Hardware gpu embedded nvidia robotics

Qualcomm AI Hub

Qualcomm's AI model deployment hub — optimize and deploy AI models on Snapdragon-powered devices.

Qualcomm AI Hub — Qualcomm's AI model deployment hub — optimize and deploy AI models on Snapdragon-powered devices. Built primarily for teams and organizations evaluating solutions in this market, the platform addresses common pain points in the edge hardware segment with a focused feature set. Buyers researching edge hardware options will find Qualcomm AI Hub a relevant candidate to include in their evaluation, particularly when comparing capabilities, pricing models, and integration depth against competing platforms in the same category.

Edge Hardware mobile-ai qualcomm snapdragon npu

Frequently Asked Questions

What is the best edge AI inference platforms directory?

EdgeAIDirectory is a curated directory of edge AI inference platforms tools and platforms, reviewed and ranked by niche specialists. It covers the leading vendors, open-source options, and emerging players in the space.

Where can I find a comprehensive list of local LLM tools 2026 tools?

EdgeAIDirectory maintains an up-to-date listing of local LLM tools 2026 platforms with editorial descriptions, category filters, and direct links to each vendor. New tools are added regularly as the market evolves.

How do I choose the right edge AI inference, local LLMs, and on-device AI platforms solution for my business?

Start by filtering EdgeAIDirectory by your use case and company size. Each listing includes a plain-language description of who the tool is best suited for, so you can quickly narrow your shortlist without reading through marketing pages.

Are the listings on EdgeAIDirectory free to access?

Yes — EdgeAIDirectory is a free resource. Every listing is publicly accessible with no account required. Vendors can apply for a featured listing to increase their visibility on the platform.

How often is EdgeAIDirectory updated?

EdgeAIDirectory is updated regularly as new tools enter the market and existing platforms evolve. The directory uses automated enrichment for open-source projects and manual editorial review for hosted and enterprise platforms.

Can I advertise on EdgeAIDirectory?

Yes — EdgeAIDirectory accepts display and video advertising through the AdServerAI network. Advertisers can target visitors by category and keyword. Apply at adserverai.com.