# Intel adds day-zero support for Meta’s Muse Spark Open > The company announced quantization support to run the 816-billion-parameter open-weight model on Xeon processors and its upcoming GPU D-series. - Canonical URL: https://newsverum.com/en/news/intel-adds-day-zero-support-for-meta-muse-spark-open - Publisher: Newsverum - Section: Technology - Country: United States - Published: 2026-10-16T10:36:24+00:00 - Updated: 2026-10-16T10:36:24+00:00 - Event / data period: 2026-10-15 - Other editions: [Türkçe](https://newsverum.com/tr/news/intel-adds-day-zero-support-for-meta-muse-spark-open.md), [العربية](https://newsverum.com/ar/news/intel-adds-day-zero-support-for-meta-muse-spark-open.md), [Français](https://newsverum.com/fr/news/intel-adds-day-zero-support-for-meta-muse-spark-open.md), [Español](https://newsverum.com/es/news/intel-adds-day-zero-support-for-meta-muse-spark-open.md), [Deutsch](https://newsverum.com/de/news/intel-adds-day-zero-support-for-meta-muse-spark-open.md), [Português](https://newsverum.com/pt/news/intel-adds-day-zero-support-for-meta-muse-spark-open.md) Intel announced on 15 October that it had day-zero support for running Meta’s open-weight Muse Spark Open model on Xeon processors and its not-yet-released GPU D-series. The company said it used low-bit quantization for CPU and GPU versions and had run the GPU version across four D-series cards. Intel describes the model as having 816 billion parameters and a one-million-token context window, and says it is aimed at coding and multimodal workflows. The company says GPU D-series is designed with 160 GB of memory per card, but describes the platform as upcoming. Intel did not publish an independent performance evaluation. ## Data ### Intel adds day-zero support for Meta’s Muse Spark Open Intel platform support for Meta’s Muse Spark Open Methodology: Model and hardware specifications are from Intel’s announcement; this is not an independent performance test, and GPU D-series has not yet launched. | date | label | description | status | |---|---|---|---| | 2026-10-15 | Announced model and accelerator | INT4 quantization on Xeon and MXFP4 support on upcoming GPU D-series for Muse Spark Open; Intel reported a four-GPU run. | occurred | Sources: · Download data: [JSON](https://newsverum.com/api/v1/articles/intel-adds-day-zero-support-for-meta-muse-spark-open/data/source-record?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/intel-adds-day-zero-support-for-meta-muse-spark-open/data/source-record?lang=en&format=csv) ## Sources - [Intel]() (Source checked: 2026-10-16; Published: 2026-10-15) --- Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)