An inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application.

Open-source libraries for applying sparsification recipes to neural networks with a few lines of code.

Open-source model repository for sparse and sparse-quantized models.

Partner with experts to ensure your ML training and deployment pipelines are optimized with SOTA research and industry best practices.

Engage, discuss, and get direct access to our engineering teams.

Explore our code on GitHub.

Get support or get started.

Explore our published research papers that are driving ML simplicity & performance.

Explore upcoming events Neural Magic will be attending. Come say hello!

Watch on-demand ML performance content on your time.

Learn about the "magic" behind Neural Magic!

Sign up for the regular Neural Magic email updates.

Explore our team and our investors.

Discover open positions. Apply or refer a friend.

Reach out to us directly.

View Neural Magic's legal documentation.