AI PORTAL
  • Models
  • Code
  • Tools

About the models on this Arm AI Portal

The Arm AI Portal (the “Portal”) provides details of AI models developed, optimized or tested for use on Arm-based platforms. Models listed on the Portal may have been developed by Arm or by third parties. Unless expressly stated otherwise, Arm did not develop or train the underlying third-party model and is not responsible for its original intended behavior or use.

Information accompanies each model listing and describes the model’s provenance, together with relevant information about the original third-party model, its developer and repository, where applicable. Inclusion on the Portal of a model developed by a third party or based on a third-party model does not constitute Arm’s endorsement or certification of that third-party model or any third-party work relating to it.

Except as expressly stated in the information accompanying a specific model, Arm makes no representation as to the accuracy, safety, security, non-infringement, legal compliance, suitability for production use or fitness for any particular purpose of any model, converted or optimized version, or related outputs.

Inclusion of a model on the Portal does not itself grant you any rights to use that model. Use of each model is subject to the applicable license terms, usage restrictions and documentation. You are responsible for reviewing that information and independently evaluating the model, its outputs and its suitability for your intended use, including compliance with applicable legal, regulatory, safety and security requirements. Any use of or reliance on a model, its outputs or related materials is at your own risk. Where the Portal links to repositories or other materials controlled by third parties, those repositories and materials are outside Arm’s control and may change without notice.

Use of the Portal is subject to the Arm Website Terms and Conditions of Use.

Code

Develop on Arm with your AI coding assistant

Arm MCP Server for AI Portal makes it faster to find optimized models, integrate code examples and deploy to your target device from your agentic coding assistant.

User guide

Run the following command in your terminal:

codex mcp add arm-ai --url https://mcp.api.devplatform.arm.com/ai-portal

Filters

Type

Device Class

Edge LinuxEthos-U NPUMobile CPUCloud CPU

Task

Text GenerationImage ClassificationAutomatic Speech RecognitionImage To ImageFeature ExtractionImage To TextObject DetectionFill MaskQuestion AnsweringImage SegmentationText To ImageText To SpeechZero Shot Image Classification
    126 results

    • Accelerate an OpenCV-based Android Application with KleidiCV

      Learning path

      Add OpenCV to an Android project and process images with routines accelerated by the KleidiCV library.

    • Accelerate Denoising, Background Blur and Low-Light Camera Effects with SME2

      Learning path

      Build denoising, background-blur, and low-light camera pipelines, then measure how SME2, KleidiAI, and KleidiCV improve real-time image processing.

    • Accelerate Generative AI workloads using KleidiAI

      Learning path

      Explore the matrix operations behind large language models and benchmark a C++ example accelerated with KleidiAI micro-kernels.

    • Accelerate LiteRT Models on Android with KleidiAI and SME2

      Learning path

      Learn how to accelerate LiteRT model inference on Android using KleidiAI with SME2 instructions and validate performance with the benchmark tool.

    • Accelerate Matrix Multiplication Performance with SME2

      Learning path

      Implement matrix multiplication in C, assembly, and intrinsics, then compare baseline and SME2-optimized performance.

    • Accelerate multimodal Voice Assistant performance with KleidiAI and SME2

      Learning path

      Build and benchmark a multimodal Android voice-assistant pipeline, then use KleidiAI and SME2 to accelerate its speech recognition and language-model components.

    • Accelerate Natural Language Processing (NLP) models from Hugging Face on Arm servers

      Learning path

      Learn how to deploy and accelerate PyTorch NLP sentiment analysis models from Hugging Face on Arm servers with BFloat16 fast math kernel optimization on Graviton3 processors.

    • Accelerate Whisper on Arm with Hugging Face Transformers

      Learning path

      This Learning Path is for software developers familiar with basic machine learning concepts and looking to run the OpenAI Whisper Automatic Speech Recognition (ASR) model efficiently, using an Arm-based cloud instance. Install the dependencies for the Whisper ASR Model.

    • Add an LLM to your Android app with Arm's AI Chat library

      Learning path

      Learn how to build an Android chatbot app using Arm's AI Chat library to run GGUF models on-device with optimized performance on Arm CPUs.

    • Analyze NFRU using Project Moku

      Learning path

      Evaluate Neural Frame Rate Upscaling quality and performance using Project Moku.

    • Anomaly detection

      Code example

      Analyze machine recordings as log-mel spectrograms and detect abnormal operating sounds with TensorFlow Lite Micro on Ethos-U.

    • Arm Neural Technology Playbook - Evaluate

      Learning path

      Evaluate whether Arm Neural Technology techniques such as NFRU and NSSD are a fit for your game.

    • Audio Generation with ExecuTorch

      Code example

      Convert Stable Audio Open Small components to ExecuTorch programs and generate short audio samples from text prompts on Arm CPUs using XNNPACK and KleidiAI.

    • Audio Generation with LiteRT

      Code example

      Convert Stable Audio Open Small components with LiteRT Torch and run text-to-audio generation on Arm CPUs through LiteRT, XNNPACK, and KleidiAI.

    • Automated Speech Recognition (ASR)

      Code example

      Transcribe recorded speech on Ethos-U using wav2letter or Conformer models with the required audio preprocessing and decoding pipeline.

    • Build a customer support chatbot on Android with Llama and ExecuTorch

      Learning path

      Learn how to build a customer support chatbot for Android using Llama 3.2, ExecuTorch, and KleidiAI to run on-device inference on Arm platforms.

    • Build a Hands-Free Selfie Android Application with MediaPipe

      Learning path

      Learn how to build a hands-free selfie Android application using MediaPipe multimodal AI, Kotlin flows, CameraX, and MVVM architecture.

    • Build a multimodal retail restocking assistant on Armv9 with MNN

      Learning path

      Learn how to build MNN on an Armv9 system, run text, vision, and audio prompts with a multimodal Omni model, and combine image and audio inputs into a single-shot retail restock ticket workflow.

    • Build a Privacy-First LLM Smart Home on Raspberry Pi 5

      Learning path

      Learn how to run large language models locally on the Raspberry Pi 5 using Ollama, control GPIO-connected devices, and deploy a privacy-first web-based smart home assistant without cloud services.

    • Build a RAG application using Zilliz Cloud on Arm servers

      Learning path

      Build a Retrieval-Augmented Generation (RAG) application on Arm servers using Zilliz Cloud for vector search and llama.cpp for LLM inference.

    • Build a RAG pipeline on Arm-based NVIDIA DGX Spark

      Learning path

      Learn how to build a Retrieval-Augmented Generation (RAG) pipeline on NVIDIA DGX Spark combining Arm Grace CPU orchestration with Blackwell GPU-accelerated inference using llama.cpp.

    • Build a Sentiment-Aware Voice Assistant with On-Device LLMs

      Learning path

      Build an end-to-end, on-device voice assistant that understands both speech and emotion using Whisper, HuBERT, ONNX Runtime, and a local LLM with llama.cpp on Arm.

    • Build an Android chat app with Llama, KleidiAI, ExecuTorch, and XNNPACK

      Learning path

      Learn how to build an Android chat application with Llama models using ExecuTorch, XNNPACK, and KleidiAI for accelerated performance on Arm smartphones.

    • Build an Android chat application with ONNX Runtime API

      Learning path

      Learn how to build ONNX Runtime and the generate() API for Android to run a Phi-3 model on Arm-based smartphones.