---
title: "Lfm2.5 Vl 3B — Vision-Language (3B) | Xybrid"
description: "Run Lfm2.5 Vl 3B on-device with Xybrid. Liquid LFM2.5-VL 3B vision-language model for local inference. Available for iOS, Android, macOS, and more."
url: "https://www.xybrid.ai/models/lfm2.5-vl-3b"
---

# Lfm2.5 Vl 3B

Vision + language · Liquid AI

Liquid LFM2.5-VL 3B vision-language model for local inference.

Model ID: `lfm2.5-vl-3b`

## 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 |
| --- | --- | --- | --- |
| [universal](https://huggingface.co/LiquidAI/LFM2.5-VL-3B-GGUF) (default) | GGUF | q4_k_m | 1.6 GB |

## The essentials

- Task: Vision + language
- Lab: Liquid AI
- Parameters: 3B
- Format: GGUF
- Quantization: `q4_k_m`
- Model file size: 1.6 GB
- Default variant: `universal`

[View on Hugging Face](https://huggingface.co/LiquidAI/LFM2.5-VL-3B-GGUF)

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