---
title: "Lfm3 Vl 2B — Vision-Language (1.9B) | Xybrid"
description: "Run Lfm3 Vl 2B on-device with Xybrid. Liquid LFM3-VL 2B vision-language model for on-device visual tasks: documents, charts, app screens and object grounding. Available for iOS, Android, macOS, and more."
url: "https://www.xybrid.ai/models/lfm3-vl-2b"
---

# Lfm3 Vl 2B

Vision + language · Liquid AI

Liquid LFM3-VL 2B vision-language model for on-device visual tasks: documents, charts, app screens and object grounding.

Model ID: `lfm3-vl-2b`

## Make it part of your app.

One model. Your language.

Image input needs its own setup: the vision guide shows how to bring this model into your app. [Read the vision guide](https://docs.xybrid.dev/en/docs/guides/vision-models)

## Available variants

| Variant | Format | Quantization | Size |
| --- | --- | --- | --- |
| [android](https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF) (default) | GGUF | q4_0 | 1001.0 MB |
| [darwin](https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF) | GGUF | q4_0 | 1001.0 MB |
| [linux](https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF) | GGUF | q4_0 | 1001.0 MB |
| [windows](https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF) | GGUF | q4_0 | 1001.0 MB |

## The essentials

- Task: Vision + language
- Lab: Liquid AI
- Parameters: 1.9B
- Format: GGUF
- Quantization: `q4_0`
- Model file size: 1001.0 MB
- Default variant: `android`

[View on Hugging Face](https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF)

Ready to build? [Read the documentation](https://docs.xybrid.dev)
