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

1

Device Class

Edge LinuxEthos-U NPUMobile CPUCloud CPU

Evaluation Target

AWS Graviton G4vivo X300Alif DK-E8Raspberry Pi 5

Arm Technology

NXSME2

Task

Text GenerationImage ClassificationObject DetectionFeature ExtractionImage-to-ImageAutomatic Speech RecognitionImage SegmentationDepth EstimationText-to-SpeechAudio ClassificationKeypoint DetectionImage-Text-to-TextText-to-ImageTranslationZero-Shot Image Classification

Vendor

Runtime

Quantization

Format

Execution Backend

Model Size

≤24.6 MB

Average Memory

≤755 MB

Peak Memory

≤796 MB
    12 results

    QuickSRNetSmall INT8

    Raspberry Pi 5

    An INT8-quantized QuickSRNetSmall image super-resolution model for upscaling low-resolution images. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-to-image41.9 KB
    ExecuTorch

    Neural Frame Rate Upscaling (NFRU)

    NX

    Neural Frame Rate Upscaling (NFRU) is an efficient network for frame rate upscaling on mobile devices. Neural Frame Rate Upscaling is a model that predicts the correct parameters needed to generate Frame T using information from Frame T-1 and Frame T+1. The model, developed by Arm, is optimized for execution on Neural Accelerators (NX) in mobile GPUs. NFRU is particularly suited for mobile gaming, XR, and other power-constrained graphics use cases.

    image-to-image125.8 KBVulkan

    SESR-M5 INT8

    Alif DK-E8

    An INT8-quantized SESR-M5 image super-resolution model for upscaling low-resolution images. Exported as an ExecuTorch program using the Ethos-U delegate for inference on Arm Ethos-U NPUs.

    image-to-image188.7 KBExecuTorch

    SESR-M5 INT8

    AWS Graviton G4

    An INT8-quantized SESR-M5 image super-resolution model for upscaling low-resolution images. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-to-image251.7 KBExecuTorch

    ESRGAN x4 INT8

    AWS Graviton G4

    INT8-quantized 4× single-image super-resolution models for enhancing low-resolution RGB images, especially urban scenes with fine repetitive details. Built on a 23-block RRDBNet backbone, they use tiled 128×128 inputs and produce 512×512 outputs per tile, balancing image fidelity with reduced model size and faster inference on ARM-oriented runtimes.

    image-to-image24.3 MBExecuTorch

    QuickSRNetSmall INT8

    AWS Graviton G4

    An INT8-quantized QuickSRNetSmall image super-resolution model for upscaling low-resolution images. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-to-image41.9 KBExecuTorch

    QuickSRNetSmall INT8

    vivo X300

    An INT8-quantized QuickSRNetSmall image super-resolution model for upscaling low-resolution images. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-to-image41.9 KBExecuTorch

    Neural Super Sampling (NSS)

    NX

    Neural Super Sampling (NSS) is a parameter prediction model for real-time temporal super sampling developed by Arm, optimized for execution on Neural Accelerators (NX) in mobile GPUs. It enables high-resolution rendering at a lower compute cost by reconstructing high-quality output frames from low-resolution temporal inputs. NSS is particularly suited for mobile gaming, XR, and other power-constrained graphics use cases.

    image-to-image167.8 KBVulkan

    SESR-M5 INT8

    vivo X300

    An INT8-quantized SESR-M5 image super-resolution model for upscaling low-resolution images. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

    image-to-image41.9 KBExecuTorch

    ESRGAN x4 INT8 (ONNX Runtime)

    AWS Graviton G4

    INT8-quantized 4x single-image super-resolution model for enhancing low-resolution RGB images, especially urban scenes with fine repetitive detail. Built on a 23-block RRDBNet backbone, it takes tiled 128x128 inputs and produces 512x512 outputs per tile, running on AWS Graviton G4 server CPUs with ONNX Runtime and its MLAS INT8 kernels.

    image-to-image24.6 MBONNX

    realesr-general-x4v3 INT8

    vivo X300SME2

    This is an INT8-quantized version of realesr-general-x4v3, a blind 4x super-resolution model from the Real-ESRGAN project (Xintao Wang et al., Tencent ARC Lab), optimized for edge deployment on ARM devices using ExecuTorch with the XNNPACK backend. The model was statically quantized (PT2E) and exported to the .pte format for efficient inference on ARM Cortex processors, including mobile devices such as the vivo X300.

    image-to-image1.4 MBExecuTorch

    QuickSRNetSmall INT8

    Alif DK-E8

    An INT8-quantized QuickSRNetSmall image super-resolution model for upscaling low-resolution images. Exported as an ExecuTorch program using the Ethos-U delegate for inference on Arm Ethos-U NPUs.

    image-to-image31.5 KBExecuTorch

    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