---
title: LFM2.5-VL-450M
canonical_url: "https://www.modelscope.cn/models/LiquidAI/LFM2.5-VL-450M"
md_url: "https://www.modelscope.cn/models/LiquidAI/LFM2.5-VL-450M.md"
repository: LiquidAI/LFM2.5-VL-450M
last_updated: 2026-04-08
license: other
pipeline_tag: image-text-to-text
tasks:
- image-text-to-text
model_type:
- lfm2_vl
architectures:
- Lfm2VlForConditionalGeneration
base_model:
- LiquidAI/LFM2.5-350M
base_model_relation: finetune
parameters: 448.7M
tensor_type:
- BF16
library_name:
- transformer
- safetensors
- pytorch
frameworks:
- pytorch
language:
- en
- ja
- ko
- fr
- es
- de
- ar
- zh
- pt
downloads: 185
stars: 1
tags:
- liquid
- lfm2
- lfm2-vl
- edge
- lfm2.5-vl
- lfm2.5
---
# LFM2.5-VL-450M
> LFM2.5-VL-450M - LiquidAI 在 ModelScope 开源的模型。Try LFM • Docs • LEAP • Discord
LiquidAI/LFM2.5-VL-450M 是 ModelScope 魔搭社区上的 448.7M 参数image-text-to-text模型，采用 other 许可，基于 LiquidAI/LFM2.5-350M 构建。
- **Repository**: LiquidAI/LFM2.5-VL-450M
- **License**: other
- **Tasks**: image-text-to-text
- **Parameters**: 448.7M
- **Base model**: LiquidAI/LFM2.5-350M
- **Tags**: liquid, lfm2, lfm2-vl, edge, lfm2.5-vl, lfm2.5
- **Downloads**: 185
- **Stars**: 1
- **Last updated**: 2026-04-08
Source: https://www.modelscope.cn/models/LiquidAI/LFM2.5-VL-450M
---
# 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| 
|
| [vLLM](https://github.com/vllm-project/vllm) | High-throughput production deployments with GPU. | Link | |
| [SGLang](https://github.com/vllm-project/vllm) | High-throughput production deployments with GPU. | Link | |
| [llama.cpp](https://github.com/ggml-org/llama.cpp) | Cross-platform inference with CPU offloading. | 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}
}
```
