Welcome to the Arm AI Optimization Challenge 2026. We’re inviting developers to build and submit projects that show how AI can be optimized for Arm-powered platforms across three challenge tracks:

Physical AI: Optimize AI for real-world systems, including robotics, embedded devices, sensors, simulation, autonomy, and edge environments.
Cloud AI: Optimize AI for scalable infrastructure, including Arm64 cloud, inference performance, frameworks, agents, and production-ready developer workflows.
Mobile AI: Optimize AI for on-device constraints, including performance, privacy, latency, battery efficiency, and local AI experiences on Arm-powered phones, tablets, and laptops.

Across all tracks, submissions should show clear optimization work and measurable improvements where possible.

Optimizations we will look for:

Model size: Reduce size on disk or in memory.

Model quality: Improve fine-tuning or output quality for a given model size.

Model speed: Improve tokens/sec, time to first token, or other relevant latency metrics.

Inference server speed: Improve throughput, latency, tokens/sec, or time to first token.

Developer experience: Improve tools, workflows, setup, documentation, or usability.

Arm-specific optimization: Implement optimizations in an existing framework, library, model, or application to run better on Arm.

Developers can use Arm Performix to get exact benchmarks of their Arm based performance and be able to clearly show their results.

Requirements

This year’s challenge has three tracks, so you can choose the path that best matches what you want to build. For more details information for each Track, please visit the Track Details Tab.

Submissions to the Hackathon must meet the following requirements:

Include a Project built with the required developer tools and meets the above Project Requirements.
Provide a URL to your code repository for judging and testing. The repository must contain all necessary source code, assets, and instructions required for the project to be functional. The repository must be public and open source by including an open source license file. This license should be detectable and visible at the top of the repository page (in the About section).
- MIT or Apache 2.0
Include a text description that should explain the features and functionality of your Project.
Project Overview: A brief description of the project and its purpose. Also explain what makes it interesting and why it should win.
Functionality / Output: Explain what the project does and what the final output is (optimized model, migration example, scavenger deliverables, etc.).
Setup Instructions: Step-by-step instructions on how to build/run/validate on an Arm-powered device or Arm64 environment (as applicable to your track).
Optional: Include a demonstration video of your Project. The video portion of the Submission:
- should be less than three (3) minutes. Judges are not required to watch beyond three minutes
- should include footage that shows the Project functioning on the device for which it was built
- must be uploaded to and made publicly visible on YouTube, Vimeo, or Youku, and a link to the video must be provided on the submission form on the Hackathon Website; and
- must not include third party trademarks, or copyrighted music or other material unless the Entrant has permission to use such material.
Track 1 & Track 2: Each submission must include a copy of the project’s source code, either attached directly or linked to an open-source repository (e.g., GitHub).
Track 3: Each submission must include proof artifacts (links/screenshots) as described in the track requirements.

Arm Create: AI Optimization Challenge

Prize breakdown

Timeline

About

Requirements

Submissions to the Hackathon must meet the following requirements: