Intel® Distribution of OpenVINO™ Toolkit

753640
2/20/2026

Introduction

This package contains the Intel® Distribution of OpenVINO™ Toolkit software version 2026.0 for Linux*, Windows*, and macOS*.

Available Downloads

  • Microsoft Windows*
  • Size: 181 MB
  • SHA256: F177E93FB35B12E47357B4EB3BB23D92F3C7BF940243137E9641D2C5E7534AEB
  • Microsoft Windows*
  • Size: 708 MB
  • SHA256: 5C5E7FCD02CE52D57F5EB45BFC33350362BA111750BBBE950598E3AD9D602D6A
  • macOS*
  • Size: 39.9 MB
  • SHA256: CA21FF94798E934A1FB6B1F295ED394FEE0321252DE029E4356DA0BA49025AAC
  • Linux*
  • Size: 36.8 MB
  • SHA256: A87A875936403ECBF3149F307F77A72163555F26CB78AB96B7B3F07E67C56578
  • Linux*
  • Size: 94.8 MB
  • SHA256: 3C99A294D1A12A96A945C56A3B27A099DF885980F7667B996CFF67B4FF3CF46A
  • Linux*
  • Size: 97.1 MB
  • SHA256: 34513AAB49957FFB1C2C840201FFA5F3952B61D13D0170CFA9D66BEF66D38C73
  • Linux*
  • Size: 67.4 MB
  • SHA256: 076ECEFACEAC388E8F96B46F7F9B6D79E136F24D6AA276EDBB892BC946956121
  • Android*
  • Size: 35.2 MB
  • SHA256: A8911D1646E926C3881B79200E6851783CF85CF5C29C6D91453EDED821B35662
  • Linux*
  • Size: 32.9 MB
  • SHA256: 71B8A470D6CEAAF1C5A9595CF57180A84996857A09FB807BFBEC8E846032D910
  • Linux*
  • Size: 70.7 MB
  • SHA256: 6F1075F2C523DEEA4EBA5B0110BB4E2F1B20B68A191BFBD9B857E185F8CC469E

Detailed Description

What’s new

  • More Gen AI coverage and frameworks integrations to minimize code changes
    • New models supported on CPUs & GPUs: GPT-OSS-20B, MiniCPM-V-4_5-8B, MiniCPM-o-2.6, and Qwen3-30B-A3B.
    • New models supported on NPUs: MiniCPM-o-2.6. In addition, NPU support is now available on Qwen2.5-1B-Instruct, Qwen3-Embedding-0.6B, and Qwen-2.5-coder-0.5B.
    • OpenVINO™ GenAI now adds word-level timestamp functionality to the Whisper Pipeline on CPUs, GPUs, and NPUs, enabling more accurate transcriptions and subtitling in line with OpenAI and FasterWhisper implementations.
    • Phi-3-mini FastDraft model is now available on Hugging Face to accelerate LLM inference on NPUs. FastDraft optimizes speculative decoding for LLMs.
  • Broader LLM model support and more model compression techniques
    • With the new int4 data-aware weight compression for 3D MatMuls, the Neural Network Compression Framework enables MoE LLMs to run with reduced memory, bandwidth, and improved accuracy compared to data-free schemes-delivering faster, more efficient deployment on resource-constrained devices.
    • Preview: the Neural Network Compression Framework now supports per-layer and per-group Look-Up Tables (LUT) for FP8-4BLUT quantization. This enables fine-grained, codebook-based compression that reduces model size and bandwidth while improving inference speed and accuracy for LLMs and transformer workloads.
  • More portability and performance to run AI at the edge, in the cloud, or locally
    • Preview: OpenVINO™ GenAI adds a VLM pipeline support to enhance Agentic AI framework integration.
    • OpenVINO GenAI now supports speculative decoding for NPUs, delivering improved performance and efficient text generation through a small draft model that is periodically validated by the full-size model.
    • Preview: NPU compiler integration with the NPU plugin enables ahead-of-time and on-device compilation without relying on OEM driver updates. Developers can enable this feature for a single, ready-to-ship package that reduces integration friction and accelerates time-to-value.
    • OpenVINO™ Model Server adds enhanced support for audio endpoint plus agentic continuous batching and concurrent runs for improved LLM performance in agentic workflows on Intel CPUs and GPUs.

Get all the details. See 2026.0 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.