Model tutorial

Step-by-step guide to download, load, and chat with models in the demo app.

LFM2-24B-A2B-Preview-GGUF

This walkthrough follows the Tutorial: LFM2-24B-A2B-Preview-GGUF section in the nexa-sdk Android README. It uses the LFM2-24B-A2B-Preview-GGUF model in the demo app.

Steps

1. Install the app

   Install the demo app (APK or build from source). For APK download and build-from-source steps, see Quick Start with APK and Build from Source on the GitHub Android README.

2. Select the model

   Open the model selector (dropdown next to the model name) and choose LFM2-24B-A2B-Preview-GGUF.

   
3. Download

   Tap Download to fetch the model to your device. Wait until the download finishes.

4. Load

   Tap Load. A load model config dialog appears: choose CPU, GPU, or NPU (for Qualcomm NPU), then tap SURE. Once the model is loaded, the chat area becomes available.

   
5. Chat

   Type your message in the input field at the bottom, then tap Send to get a response. Use Clear to clear the input or conversation as needed.

   

Was this page helpful?

Yes

No