---
title: LFM2-24B-A2B-GGUF
canonical_url: "https://www.modelscope.ai/models/NexaAI/LFM2-24B-A2B-GGUF"
md_url: "https://www.modelscope.ai/models/NexaAI/LFM2-24B-A2B-GGUF.md"
repository: NexaAI/LFM2-24B-A2B-GGUF
last_updated: 2026-02-25
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
base_model:
  - LiquidAI/LFM2-24B-A2B-Preview
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - ar
  - zh
  - fr
  - de
  - ja
  - ko
  - es
downloads: 180
stars: 0
tags:
  - liquid
  - lfm2
  - edge
  - moe
  - llama.cpp
  - gguf
---

# LFM2-24B-A2B-GGUF

> LFM2-24B-A2B-GGUF - An open-source model by NexaAI on ModelScope. LFM2-24B-A2B-Preview-GGUF

NexaAI/LFM2-24B-A2B-GGUF is a text-generation model on ModelScope. licensed under other. derived from LiquidAI/LFM2-24B-A2B-Preview.

- **Repository**: NexaAI/LFM2-24B-A2B-GGUF
- **License**: other
- **Tasks**: text-generation
- **Base model**: LiquidAI/LFM2-24B-A2B-Preview
- **Tags**: liquid, lfm2, edge, moe, llama.cpp, gguf
- **Downloads**: 180
- **Stars**: 0
- **Last updated**: 2026-02-25

Source: https://www.modelscope.ai/models/NexaAI/LFM2-24B-A2B-GGUF

---

# LFM2-24B-A2B-Preview-GGUF

LFM2-24B-A2B-Preview in GGUF format for use with [NexaSDK](https://github.com/NexaAI/nexa-sdk), with support for Qualcomm NPU, GPU, and CPU inference.

## Model

This repository contains the LFM2 24B parameter model with A2B quantization in GGUF format. It is intended for on-device inference via NexaSDK on Android, Windows, and other supported platforms.

## NPU Setup

**Hardware:** Qualcomm Snapdragon 8 Gen 4 (or other Snapdragon SoCs with NPU as documented by Nexa).

## Tutorial: Run on Android demo app

1. **Install the app**  
   Install the [NexaSDK Android demo app](https://github.com/NexaAI/nexa-sdk/tree/main/bindings/android).

   **Option A — APK:** Download the pre-built APK and install via adb:
   ```bash
   # Download: https://nexa-model-hub-bucket.s3.us-west-1.amazonaws.com/public/android-demo-release/nexaai-demo-app.apk
   adb install nexaai-demo-app.apk
   ```

   **Option B — Build from source:** Clone the repo, open `bindings/android` in Android Studio, then build and run. See the [Android demo README](https://github.com/NexaAI/nexa-sdk/tree/main/bindings/android) for full steps.

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.

For NPU/GPU/CPU requirements and license, see [NPU Setup](#npu-setup) above and [Android SDK Doc](https://docs.nexa.ai/nexa-sdk-android/overview).

For the full tutorial with screenshots, see the [Tutorial: LFM2-24B-A2B-Preview-GGUF](https://github.com/NexaAI/nexa-sdk/blob/main/bindings/android/README.md#tutorial-lfm2-24b-a2b-preview-gguf) section in the Android demo README on GitHub.

## Usage

- **Android:** See [NexaSDK Android documentation](https://docs.nexa.ai/nexa-sdk-android/overview) for running this model on devices with NPU or other backends.
- **PC / other platforms:** See [NexaSDK](https://github.com/NexaAI/nexa-sdk) for CLI and bindings.