Skip to model comparison
AI Agent Store/Model comparisonsBuild an AI worker ↗

OpenMobile-2 · Download verified

OpenMobile 2 9B

Build an Android assistant that reads screenshots and takes actions in apps. Your application connects the model to the phone and decides which actions it may execute.

First reviewed 2026-10-26 · Checked 2026-11-03. The launch date has not been confirmed.

We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Try it on your hardware and tasks before relying on it.

Runs onYour hardwareHardware and setup costs apply
Documented capacityNot verifiedSee input limits below

What you can use today

You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.

Exact download ID: OpenMobile-2/OpenMobile-2-9B. Can select screen actions and call app-specific tools when the app currently open makes them available. Use the matching agent software and test complete workflows, including mistakes and recovery.

Downloadable weights are labelled Apache 2.0. The 9B version builds on Qwen3.5-9B; 27B builds on Qwen3.6-27B. Their scores cannot be substituted for one another or for the parent models.

The publisher’s serving examples use a 65,536-token input-and-answer budget. That example does not establish the model’s maximum supported context or output.

No hosted token price is established. For local use, include hardware, electricity and setup time in your budget.

Provider release and specifications ↗

Check availability and plans ↗

Provider documentation ↗

More setup and licensing details ↗

Test it before switching

Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.

Compare caching and long-context costs ↗
AI Agent Store · Model comparisons · Data reviewed 2026-11-03Sources, limitations & corrections ↗