onnx-community/LFM2.5-VL-450M-ONNX

Try LFM • Docs • LEAP • Discord

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]);

See example output

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.

🔧 Fine-tuning

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

Notebook	Description	Link
SFT (Unsloth)	Supervised Fine-Tuning with LoRA using Unsloth.
SFT (TRL)	Supervised Fine-Tuning with LoRA using TRL.

📊 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

Model	MMStar	RealWorldQA	MMBench (dev en)	MMMU (val)	POPE	MMVet	BLINK	InfoVQA (val)	OCRBench	MM-IFEval	MMMB	CountBench	RefCOCO-M
LFM2.5-VL-450M	43.00	58.43	60.91	32.67	86.93	41.10	43.92	43.02	684	45.00	68.09	73.31	81.28
LFM2-VL-450M	40.87	52.03	56.27	34.44	83.79	33.85	42.61	44.56	657	33.09	54.29	47.64	-
SmolVLM2-500M	38.20	49.90	52.32	34.10	82.67	29.90	40.70	24.64	609	11.27	46.79	61.81	-

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

Model	GPQA	MMLU Pro	IFEval	Multi-IF	BFCLv4
LFM2.5-VL-450M	25.66	19.32	61.16	34.63	21.08
LFM2-VL-450M	23.13	17.22	51.75	26.21	-
SmolVLM2-500M	23.84	13.57	30.14	6.82	-

📬 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}
}