--- library_name: transformers license: other license_name: lfm1.0 license_link: LICENSE language: - en - ja - ko - fr - es - de - ar - zh - pt pipeline_tag: image-text-to-text tags: - liquid - lfm2 - lfm2-vl - edge - lfm2.5-vl - lfm2.5 base_model: LiquidAI/LFM2.5-350M ---

Try LFM • Docs • LEAP • Discord

# LFM2.5‑VL-450M LFM2.5‑VL-450M is [Liquid AI](https://www.liquid.ai/)'s refreshed version of the first vision-language model, [LFM2-VL-450M](https://huggingface.co/LiquidAI/LFM2-VL-450M), built on an updated backbone [LFM2.5-350M](https://huggingface.co/LiquidAI/LFM2.5-350M) and tuned for stronger real-world performance. Find more about LFM2.5 family of models in our [blog post](http://www.liquid.ai/blog/lfm2-5-vl-450m). * **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](https://huggingface.co/spaces/LiquidAI/LFM2.5-VL-450M-WebGPU) 🎥⚡️ Alternatively, try the API model on the [Playground](https://playground.liquid.ai/chat?model=lfm2.5-vl-450m). ## 📄 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` | Model | Description | |-------|-------------| | [**LFM2.5-VL-450M**](https://huggingface.co/LiquidAI/LFM2.5-VL-450M) | Original model checkpoint in native format. Best for fine-tuning or inference with Transformers and vLLM. | | [LFM2.5-VL-450M-GGUF](https://huggingface.co/LiquidAI/LFM2.5-VL-450M-GGUF) | Quantized format for llama.cpp and compatible tools. Optimized for CPU inference and local deployment with reduced memory usage. | | [LFM2.5-VL-450M-ONNX](https://huggingface.co/LiquidAI/LFM2.5-VL-450M-ONNX) | ONNX Runtime format for cross-platform deployment. Enables hardware-accelerated inference across diverse environments (cloud, edge, mobile). | | [LFM2.5-VL-450M-MLX-8bit](https://huggingface.co/LiquidAI/LFM2.5-VL-450M-MLX-8bit) | MLX format for Apple Silicon. Optimized for fast on-device inference on Mac with [mlx-vlm](https://github.com/Blaizzy/mlx-vlm). Also available in [4bit](https://huggingface.co/LiquidAI/LFM2.5-VL-450M-MLX-4bit), [5bit](https://huggingface.co/LiquidAI/LFM2.5-VL-450M-MLX-5bit), [6bit](https://huggingface.co/LiquidAI/LFM2.5-VL-450M-MLX-6bit), and [bf16](https://huggingface.co/LiquidAI/LFM2.5-VL-450M-MLX-bf16). | 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](https://docs.liquid.ai/lfm/key-concepts/chat-template#vision-models) for details. ``` <|startoftext|><|im_start|>system You are a helpful multimodal assistant by Liquid AI.<|im_end|> <|im_start|>user 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()`](https://huggingface.co/docs/transformers/en/chat_templating_multimodal) to format your messages automatically. ## 🏃 Inference You can run LFM2.5-VL-450M with Hugging Face [`transformers`](https://github.com/huggingface/transformers) v5.1 or newer: ```bash pip install transformers pillow ``` ```python from transformers import AutoProcessor, AutoModelForImageTextToText from transformers.image_utils import load_image # Load model and processor model_id = "LiquidAI/LFM2.5-VL-450M" model = AutoModelForImageTextToText.from_pretrained( model_id, device_map="auto", dtype="bfloat16" ) processor = AutoProcessor.from_pretrained(model_id) # Load image and create conversation url = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" image = load_image(url) conversation = [ { "role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": "What is in this image?"}, ], }, ] # Generate Answer inputs = processor.apply_chat_template( conversation, add_generation_prompt=True, return_tensors="pt", return_dict=True, tokenize=True, ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=64) processor.batch_decode(outputs, skip_special_tokens=True)[0] # This image captures the iconic Statue of Liberty standing majestically on Liberty Island in New York City. The statue, a symbol of freedom and democracy, is prominently featured in the foreground, its greenish-gray hue contrasting beautifully with the surrounding water. ``` ### Visual grounding LFM2.5-VL-450M supports bounding box prediction: ```python url = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" image = load_image(url) query = "status" prompt = f'Detect all instances of: {query}. Response must be a JSON array: [{"label": ..., "bbox": [x1, y1, x2, y2]}, ...]. Coordinates are normalized to [0,1].' conversation = [ { "role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": prompt}, ], }, ] # Generate Answer inputs = processor.apply_chat_template( conversation, add_generation_prompt=True, return_tensors="pt", return_dict=True, tokenize=True, ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=64) processor.batch_decode(outputs, skip_special_tokens=True)[0] # [{"label": "statue", "bbox": [0.3, 0.25, 0.4, 0.65]}] ``` ### Tool Use LFM2.5 supports function calling for text only input by applying the chat template with the tokenizer. See the [Tool Use documentation](https://docs.liquid.ai/lfm/key-concepts/tool-use) for the full guide. ```python tools = [{ "name": "get_weather", "description": "Get current weather for a location", "parameters": { "type": "object", "properties": {"location": {"type": "string"}}, "required": ["location"] } }] messages = [{"role": "user", "content": "What's the weather in Paris?"}] # Apply chat template with tools inputs = processor.tokenizer.apply_chat_template( messages, tools=tools, add_generation_prompt=True, return_tensors="pt", return_dict=True, ) input_ids = inputs["input_ids"].to(model.device) outputs = model.generate(input_ids, max_new_tokens=256) response = processor.tokenizer.decode(outputs[0, input_ids.shape[1]:], skip_special_tokens=False) # <|tool_call_start|>[get_weather(location="Paris")]<|tool_call_end|>I am retrieving the current weather for Paris.<|im_end|> ``` | Name | Description | Docs | Notebook | |------|-------------|------|----------| | [Transformers](https://github.com/huggingface/transformers) | Simple inference with direct access to model internals. | Link|

| ## 🔧 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](https://github.com/open-compass/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](https://discord.com/invite/liquid-ai) - If you are interested in custom solutions with edge deployment, please contact [our sales team](https://www.liquid.ai/contact). ## Citation ``` @article{liquidai2025lfm2, title={LFM2 Technical Report}, author={Liquid AI}, journal={arXiv preprint arXiv:2511.23404}, year={2025} } ```