Release

Intel releases OpenVINO 2026.4 with multi-token prediction decoding in OpenVINO GenAI

Event: Sep 16, 2026 · Published: Oct 13, 2026

Intel published OpenVINO 2026.4.0 on GitHub on September 16, 2026. The release notes say OpenVINO GenAI adds Multi-Token Prediction (MTP) speculative decoding for Gemma 4, Qwen3.5 and Qwen3.6 on CPUs and GPUs, and introduces DFlash acceleration for Qwen models on GPUs as a preview. Newly supported models on CPU and GPU include Kokoro-82M, Qwen3-ASR, Muse Glimmer 30B, Qwen3.8 27B and Gemma 4 12B. OpenVINO GenAI also adds an ASRPipeline for Node.js, and the notes say support for Python 3.10 will be discontinued in OpenVINO 2026.5. USASI has not tested this release.1

Sources

1.
OpenVINO 2026.4.0 (GitHub release notes) (external site: github.com)
Intel (OpenVINO toolkit on GitHub) · Release notes · published Sep 16, 2026 · accessed Oct 13, 2026

Email a correction Report a correction Edit this entry

All news

Cite this page

APA style

USASI. (2026, October 13). Intel releases OpenVINO 2026.4 with multi-token prediction decoding in OpenVINO GenAI. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/news/intel-releases-openvino-2026-4/

BibTeX

@misc{usasi_news_intel_releases_openvino_2026_4,
  author = {{USASI}},
  title = {Intel releases OpenVINO 2026.4 with multi-token prediction decoding in OpenVINO GenAI},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/news/intel-releases-openvino-2026-4/}},
  note = {United States of America Superintelligence. Last updated 2026-10-13}
}

The date is when this page was last updated. Add the date you read it if your style needs one.

Related catalog entries

Sources

Share or cite this page

Support Us