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.

Models

Filters

3

Device Class

Edge LinuxMobile CPUCloud CPU

Evaluation Target

Raspberry Pi 5vivo X300AWS Graviton G4

Arm Technology

No Arm technologies available

Task

Image ClassificationObject DetectionImage SegmentationFeature ExtractionImage-to-ImageAutomatic Speech RecognitionDepth EstimationKeypoint DetectionText GenerationText-to-ImageZero-Shot Image Classification

Vendor

Runtime

Quantization

Format

Execution Backend

Model Size

≤88 MB

Average Memory

≤108 MB

Peak Memory

≤135 MB
    21 results

    ResNet-50 INT8

    Raspberry Pi 5

    INT8-quantized 50-layer residual network for 1000-class image classification. It uses symmetric per-channel quantization with XNNPACK support, accepts 224×224 RGB inputs with ImageNet normalization, and returns raw logits for class prediction.

    image-classification25.9 MB
    ExecuTorch

    ResNet-18 INT8

    Raspberry Pi 5

    INT8-quantized 18-layer residual network for 1000-class image classification, optimized for efficient ARM edge inference with ExecuTorch and the XNNPACK backend. It uses 224×224 RGB inputs with ImageNet normalization and returns logits for top-k prediction, offering a much smaller, faster, and lower-memory alternative to the FP32 baseline while retaining comparable classification quality.

    image-classification11.8 MBExecuTorch

    Wide ResNet-50 INT8

    vivo X300

    An INT8-quantized Wide ResNet-50 image classification model using a widened residual convolutional network for visual feature extraction. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-classification50.6 MBExecuTorch

    Inception v3 INT8

    Raspberry Pi 5

    An INT8-quantized Inception v3 convolutional image classification model using factorized convolutions for visual feature extraction. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-classification25.4 MBExecuTorch

    MobileNetV3-Small INT8

    Raspberry Pi 5

    A compact INT8 image-classification CNN using inverted residual blocks, Squeeze-and-Excitation modules, and hard-swish activations to deliver efficient 1,000-class visual recognition with low compute and memory requirements.

    image-classification2.8 MBExecuTorch

    EfficientNet-B4 INT8

    Raspberry Pi 5

    An INT8-quantized EfficientNet-B4 convolutional image classification model for visual recognition. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-classification22.8 MBExecuTorch

    SqueezeNet 1.1 INT8

    Raspberry Pi 5

    An INT8-quantized, fire-module CNN for efficient 1000-class image classification, using per-channel weights and per-tensor activations. It provides a compact, low-latency alternative to its FP32 counterpart with minimal accuracy impact, fixed 224×224 image inputs, and standard softmax-based top-class prediction outputs.

    image-classification1.3 MBExecuTorch

    Wide ResNet-50 INT8

    Raspberry Pi 5

    An INT8-quantized Wide ResNet-50 image classification model using a widened residual convolutional network for visual feature extraction. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-classification72.7 MBExecuTorch

    SqueezeNet 1.0 INT8

    Raspberry Pi 5

    An INT8-quantized SqueezeNet 1.0 compact convolutional image classification model using fire modules for visual feature extraction. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-classification1.4 MBExecuTorch

    EfficientViT INT8

    Raspberry Pi 5

    An INT8-quantized EfficientViT image classification model for visual recognition. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-classification19 MBExecuTorch

    GoogLeNet INT8

    AWS Graviton G4

    INT8-quantized image classification models based on an Inception-style convolutional architecture, designed to reduce model size while preserving accuracy close to the original FP32 variant. They accept 224×224 RGB inputs with standard ImageNet preprocessing and output raw logits for 1,000 classes.

    image-classification6.8 MBExecuTorch

    DeiT-Tiny INT8

    Raspberry Pi 5

    INT8-quantized compact vision transformer for 1000-class image classification, designed for efficient inference on ARM edge devices with ExecuTorch and XNNPACK. It uses static symmetric per-channel quantization and ImageNet-style preprocessing, producing raw logits for top-k classification while reducing model size, latency, and memory use with minimal accuracy impact compared with the FP32 baseline.

    image-classification6.9 MBExecuTorch

    ViT-Base INT8

    Raspberry Pi 5

    INT8-quantized Vision Transformer for 1000-class image classification, using 16×16 image patches at 224×224 resolution. It is designed for efficient edge inference on ARM devices with XNNPACK acceleration, producing raw ImageNet logits from RGB inputs while preserving accuracy with a much smaller, faster, and lower-memory footprint than the FP32 baseline.

    image-classification88 MBExecuTorch

    ConvNeXt INT8

    Raspberry Pi 5

    An INT8-quantized ConvNeXt convolutional image classification model for visual recognition. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-classification71.7 MBExecuTorch

    ShuffleNetV2 x1.0 INT8

    Raspberry Pi 5

    A lightweight INT8-quantized convolutional image-classification model using channel split, depthwise convolution, and channel shuffle operations to improve efficiency while preserving strong 1000-class recognition capability. Designed for compact, low-latency inference with fixed 224×224 RGB inputs and ImageNet-style preprocessing.

    image-classification2.5 MBExecuTorch

    Swin Tiny INT8

    Raspberry Pi 5

    An INT8-quantized hierarchical Vision Transformer for 1000-class image classification, using shifted-window attention for efficient visual representation. Weights are quantized per channel and activation scales are computed at runtime, giving a compact, faster alternative to the original FP32 model with fixed 224×224 RGB inputs and softmax-based top-class predictions.

    image-classification29.9 MBExecuTorch

    GoogLeNet INT8

    vivo X300

    An INT8-quantized GoogLeNet image classification model based on an Inception-style convolutional architecture. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-classification5.6 MBExecuTorch

    ViT-B/16 INT8

    vivo X300

    An INT8-quantized ViT-B/16 Vision Transformer for image classification, using 16-by-16 image patches for visual feature extraction. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-classification51.4 MBExecuTorch

    Inception V3 INT8

    AWS Graviton G4

    INT8-quantized image-classification family for 1,000-class ImageNet-style recognition, using static quantization with per-channel weights and per-tensor activations to reduce size, latency, and memory use while preserving high top-k prediction quality. Inputs are RGB images resized and cropped to 299×299, with outputs as raw class logits.

    image-classification24.2 MBExecuTorch

    Wide ResNet-50 INT8

    AWS Graviton G4

    An INT8-quantized Wide ResNet-50 image classification model using a widened residual convolutional network for visual feature extraction. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-classification50.6 MBExecuTorch

    GoogLeNet INT8

    Raspberry Pi 5

    An INT8-quantized Inception v1 image-classification model with per-channel weights and per-tensor activations. It accepts 224×224 RGB ImageNet-style inputs and produces raw logits over 1,000 classes, preserving the original preprocessing behavior with a single logits output.

    image-classification6.8 MBExecuTorch

    Develop on Arm with your AI coding assistant

    The Arm AI Portal MCP Server 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