Intel® Distribution of OpenVINO™ Toolkit

753640
8/26/2026

Introduction

This package contains the Intel® Distribution of OpenVINO™ Toolkit software version 2026.3 for Linux*, Windows*, and macOS*.

Available Downloads

  • Microsoft Windows*
  • Size: 217.5 MB
  • SHA512: c05b21dbedb2b971e4b0a954cc5d2a9845cc08284b4590b069190ecdb5ed5a890ba3c49a031990a8ee296050e6634c667832893f301cb8b0ffc54ede79b53a0a
  • Microsoft Windows*
  • Size: 224.2 MB
  • SHA512: a603826088a5e49a819cd2047a35eab775c5e35f610bbf57ca62c885b91760d8fb58063e4335278a844575aa45e51a8bec11cb0489c095078a771e9face631db
  • Microsoft Windows*
  • Size: 1.5 GB
  • SHA512: 828205cfa9400b20dbf20d88e781a8d242fc7e85a9f498b5a98d80b08d2e9506a8c432ba8569ae37d02ff44b8ca34bceaa2e8f558fbc6c1fdc4aa93bd733a048
  • Microsoft Windows*
  • Size: 1.5 GB
  • SHA512: 4ad6a230ec836cbe1dee92865eac8e195371792460bafab9164355be7db9bf884dc93e8c5385183079de65f4d88274531e9a624011b1bd239bb42bee0780c839
  • macOS*
  • Size: 42.4 MB
  • SHA512: ae70d54490f4f57c4e93ae3b7104b2b30f13899caa1c08575f0b83cb2dbeb73331935cfee5886990f873287bbbeb2a2bbfe73960fc80bf39d27e05230a8f31df
  • Ubuntu 22.04 LTS*
  • Size: 41.4 MB
  • SHA512: c3b72fa3f20460b22fb304197d65fdfc021c24feb5e8317944177cd83b0711b261574345687fb7452c70610fe3f6da4be3ea3fa8f9b405596f21dda9be44532e
  • CentOS 8 (1905)*
  • Size: 73.3 MB
  • SHA512: f28a668aec10604cf8677f68d02d2fe04c7d615f0a6eb7c1b42049558ca356595360704659ab0a899713e5e87f5776d8ea87ddc989daa8a7ccdf12091cc9cd20
  • Android*
  • Size: 42 MB
  • SHA512: c0edf6f79cb7c0cefc5375839317c5731f2e7eeb5096ea8215399360ffc799ba2e3f95cf0b2a62fddfc667e4314c8c60dd9ffd954895cf6bc3d562b607a5e911
  • Red Hat Enterprise Linux 8.3*
  • Size: 76.9 MB
  • SHA512: 62a20caf77b3324689cf0ac57043cab95ff1865182ce3d6a3f399060683e751414e82e255874b0ab02b27a17dc0bada949e6cfe53fe502bd2090453be31d6b0e
  • Red Hat Enterprise Linux 8*
  • Size: 68.1 MB
  • SHA512: 9b970d3d5c05679e779e25baba5716a8d8ebe931d1a492c7e78511270f75b9f419c1cc2d3b4adbc4347d3db6b50ed2325ef7e3a92851519ccc43dcf916cf740a
  • Ubuntu 22.04 LTS*
  • Size: 112.4 MB
  • SHA512: f8adb232cc40198ecf94085b5be7b2c5f6a920630fb1ecd299884182f0317e48b09255108317ae8614f334aa7982ff908f3c2fece5188361124ed10fcdf24b41
  • Ubuntu 24.04 LTS*
  • Size: 115 MB
  • SHA512: 2e0f85424d1b0ba8c58617ff8150c6abf0e0c8735fa6e666a5b1af1629098bfb2fcb7bfb7d22e2bb9eb509d6e9d032b3540de8aa03bd37315f38b1981a6b78a2
  • Ubuntu 24.04 LTS*
  • Size: 118.8 MB
  • SHA512: 54c999839d5ccb7122237cf3b575e99e2e8bd35881f56d1aa527ad34b7e4134638ad69f2925e9cefffb562348c475069a5e69dcc0e55e6faf0fb834c0cb4fd7e

Detailed Description

What’s New

  • More Gen AI coverage and frameworks integrations to minimize code changes

    • New models supported:

      • On CPU, GPU, and NPU: SmolLM3-3B, LFM2-1.2B, LFM2.5-1.2B

      • On CPU and GPU: Harrier OSS-v1-0.6B, Qwen3-8B with EAGLE-3, MiniCPM5-1B, FLUX.2-klein-4B

      • Extended to GPU and NPU: YOLO26

      • Additional models available as early releases on CPU and GPU: Qwen3-ASR, Qwen3-Omni, Gemma-3n, Qwen3-VL-Embedding-8B, Kokoro-82M

    • Support for Hugging Face Transformers v5.5, ensuring compatibility with the latest model architectures on Hugging Face

    Broader LLM model support and more model compression techniques

    • OpenVINO™ GenAI extends the EAGLE-3 speculative decoding pipeline to LLMs and VLMs, enhancing existing continuous batching and adding Top-K sampling to deliver additional token-generation speedups on CPUs, GPUs, and NPUs.

    • Lazy weight loading is enabled for IR and ONNX models to automatically select an optimal loading and compilation path, minimizing peak memory usage during model initialization.

    • Neural Network Compression Framework (NNCF) now supports FP8 quantization for ONNX models, helping developers realize FP8 performance, accuracy, and memory gains while expanding low-precision inference options for production deployments.

    • OpenVINO™ GenAI now supports three additional pipelines: Omni for multimodal workloads, ASR for speech recognition, and Embedding for multimodal embedding generation.

    More portability and performance to run AI at the edge, in the cloud or locally

    • Introducing support for Intel® Xeon® 6+ processors (formerly codenamed Clearwater Forest)

    • MoE offloading to disk enabled, allowing 30B MoE models like Qwen3-30B-A3B to run even on devices with 16 GB of memory while maintaining acceptable tokens-per-second (TPS) generation rates.

    • OpenVINO™ Model Server simplifies model deployment and unifies REST API endpoints, reducing command complexity while providing standard v1/chat/completions support for easier integration with other serving frameworks.

    • OpenVINO™ Model Server further improves stability, performance, and accuracy for LLMs such as Qwen3.5/3.6 with linear attention and extends tool-parser support to MiniCPM5-1B and LFM2.5, improving accuracy and reliability.

Get all the details. See 2026.3 release notes.

Installation instructions

You can choose how to install OpenVINO™ Runtime from Archive* according to your operating system:

What's included in the download package (Archive File)

  • Offers both C/C++ and Python APIs
  • Additionally includes code samples

 

Helpful Links

NOTE: Links open in a new window.

Disclaimers1

Product and Performance Information

1

Intel is in the process of removing non-inclusive language from our current documentation, user interfaces, and code. Please note that retroactive changes are not always possible, and some non-inclusive language may remain in older documentation, user interfaces, and code.