LFM2.5-VL-450M-ONNX

<center> <div style="text-align: center;"> <img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" alt="Liquid AI" style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;" /> </div> <div style="display: flex; justify-content: center; gap: 0.5em;"> <a href="https://playground.liquid.ai/chat?model=lfm2.5-vl-450m"><strong>Try LFM</strong></a> • <a href="https://docs.liquid.ai/lfm/getting-started/welcome"><strong>Docs</strong></a> • <a href="https://leap.liquid.ai/"><strong>LEAP</strong></a> • <a href="https://discord.com/invite/liquid-ai"><strong>Discord</strong></a> </div> </center> <br>

LFM2.5‑VL-450M

LFM2.5‑VL-450M is Liquid AI's refreshed version of the first vision-language model, LFM2-VL-450M, built on an updated backbone LFM2.5-350M and tuned for stronger real-world performance. Find more about LFM2.5 family of models in our blog post.

• Enhanced instruction following on vision and language tasks.
• Improved multilingual vision understanding in Arabic, Chinese, French, German, Japanese, Korean, Portuguese and Spanish.
• Bounding box prediction and object detection for grounded visual understanding.
• Function calling support for text-only input.

🎥⚡️ You can try LFM2.5-VL-450M running locally in your browser with our real-time video stream captioning WebGPU demo 🎥⚡️

Alternatively, try the API model on the Playground.

📄 Model details

LFM2.5-VL-450M is a general-purpose vision-language model with the following features:

• LM Backbone: LFM2.5-350M
• Vision encoder: SigLIP2 NaFlex shape‑optimized 86M
• Context length: 32,768 tokens
• Vocabulary size: 65,536
• Languages: English, Arabic, Chinese, French, German, Japanese, Korean, Portuguese, and Spanish
• Native resolution processing: handles images up to 512*512 pixels without upscaling and preserves non-standard aspect ratios without distortion
• Tiling strategy: splits large images into non-overlapping 512×512 patches and includes thumbnail encoding for global context
• Inference-time flexibility: user-tunable maximum image tokens and tile count for speed/quality tradeoff without retraining
• Generation parameters:
  • text: temperature=0.1, min_p=0.15, repetition_penalty=1.05
  • vision: min_image_tokens=32 max_image_tokens=256, do_image_splitting=True

We recommend using it for general vision-language workloads, captioning and object detection. It’s not well-suited for knowledge-intensive tasks or fine-grained OCR.

Chat Template

LFM2.5-VL uses a ChatML-like format. See the Chat Template documentation for details.

<|startoftext|><|im_start|>system
You are a helpful multimodal assistant by Liquid AI.<|im_end|>
<|im_start|>user
<image>Describe this image.<|im_end|>
<|im_start|>assistant
This image shows a Caenorhabditis elegans (C. elegans) nematode.<|im_end|>

You can use processor.apply_chat_template() to format your messages automatically.

🏃 Inference

You can run LFM2.5-VL-450M with Hugging Face transformers.js v4.2.1 or newer:

npm i @huggingface/transformers

You can then use the model as follows:

import {
  AutoProcessor,
  AutoModelForImageTextToText,
  load_image,
  TextStreamer,
} from "@huggingface/transformers";

// Load processor and model
const model_id = "onnx-community/LFM2.5-VL-450M-ONNX";
const processor = await AutoProcessor.from_pretrained(model_id);
const model = await AutoModelForImageTextToText.from_pretrained(model_id, {
  device: "webgpu",
  dtype: {
    embed_tokens: "fp16",
    decoder_model_merged: "q4f16",
    vision_encoder: "fp16",
  },
});

// processor.image_processor.do_image_splitting = false; // Disable image splitting for this demo (faster)

const messages = [
  {
    role: "user",
    content: [
      { type: "image" },
      { type: "text", text: "Describe this image." },
    ],
  },
];
const prompt = processor.apply_chat_template(messages, {
  add_generation_prompt: true,
});

// Prepare inputs
const url = "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/artemis.jpeg";
const image = await load_image(url);
const inputs = await processor(image, prompt, { add_special_tokens: false });

const outputs = await model.generate({
  ...inputs,
  max_new_tokens: 2048,
  streamer: new TextStreamer(processor.tokenizer, {
    skip_prompt: true,
    // callback_function: (text) => { /* Do something with the streamed output */ },
  }),
});

// Decode output
const decoded = processor.batch_decode(
  outputs.slice(null, [inputs.input_ids.dims.at(-1), null]),
  { skip_special_tokens: true },
);
console.log(decoded[0]);

<details> <summary>See example output</summary>

This image captures a dramatic scene of an American flag prominently displayed on a flagpole against a clear, cloudless blue sky. The flag, with its iconic red and white stripes and blue field adorned with white stars, is fluttering in the wind, suggesting a strong breeze. The flagpole, which is black and topped with a spherical finial, supports the flag at an angle, with the flag fluttering to the left.

In the background, a rocket is seen launching into the sky, its nose pointed upwards and emitting a bright, white flame. The rocket's exhaust trails a vivid orange and yellow, creating a striking contrast against the clear blue sky. The image is taken from a low angle, emphasizing the flag's movement and the rocket's ascent, capturing a moment of national pride and technological achievement.

</details>

🔧 Fine-tuning

We recommend fine-tuning LFM2.5-VL-450M model on your use cases to maximize performance.

📊 Performance

LFM2.5-VL-450M improves over LFM2-VL-450M across both vision and language benchmarks, while also adding two new capabilities: bounding box prediction on RefCOCO-M and function calling support measured by BFCLv4.

Vision benchmarks

All vision benchmark scores are obtained using VLMEvalKit. Multilingual scores are based on the average of benchmarks translated by GPT-4.1-mini from English to Arabic, Chinese, French, German, Japanese, Korean, Portuguese, and Spanish.

Language benchmarks

📬 Contact

• Got questions or want to connect? Join our Discord community
• If you are interested in custom solutions with edge deployment, please contact our sales team.

Citation

@article{liquidai2025lfm2,
 title={LFM2 Technical Report},
 author={Liquid AI},
 journal={arXiv preprint arXiv:2511.23404},
 year={2025}
}