Instructions to use LiquidAI/LFM2-VL-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM2-VL-3B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="LiquidAI/LFM2-VL-3B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("LiquidAI/LFM2-VL-3B")
model = AutoModelForMultimodalLM.from_pretrained("LiquidAI/LFM2-VL-3B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LiquidAI/LFM2-VL-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM2-VL-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LiquidAI/LFM2-VL-3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM2-VL-3B

SGLang

How to use LiquidAI/LFM2-VL-3B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "LiquidAI/LFM2-VL-3B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LiquidAI/LFM2-VL-3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "LiquidAI/LFM2-VL-3B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LiquidAI/LFM2-VL-3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use LiquidAI/LFM2-VL-3B with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2-VL-3B
```

EdoardoMosca commited on Oct 22, 2025

Commit

d082f35

verified ·

1 Parent(s): 67c26e7

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -30,8 +30,8 @@ Built on the [LFM2](https://huggingface.co/collections/LiquidAI/lfm2-686d7219270
 We are releasing the weights of the new [3B](https://huggingface.co/LiquidAI/LFM2-VL-3B) checkpoint—offering higher performance across benchmarks while remaining optimized for scalable deployment.
-* **State-of-the-art multimodal performance** within the lightweight model range
-* **Enhanced reasoning and visual comprehension**, especially on fine-grained visual tasks
 * **Retains efficient inference** with the same flexible architecture and user-tunable speed-quality tradeoffs
 * **Processes native resolutions up to 512×512** with intelligent patch-based handling for larger inputs
@@ -90,10 +90,10 @@ You can apply it using the dedicated [`.apply_chat_template()`](https://huggingf
 ## 🏃 How to run LFM2-VL
-You can run LFM2-VL with Hugging Face [`transformers`](https://github.com/huggingface/transformers) v4.57 or more recent as follows:
 ```bash
-pip install -U transformers pillow
 ```
 Here is an example of how to generate an answer with transformers in Python:

 We are releasing the weights of the new [3B](https://huggingface.co/LiquidAI/LFM2-VL-3B) checkpoint—offering higher performance across benchmarks while remaining optimized for scalable deployment.
+* **Competitive multimodal performance** among lightweight open models.
+* **Enhanced visual understanding and reasoning**, particularly on fine-grained perception tasks
 * **Retains efficient inference** with the same flexible architecture and user-tunable speed-quality tradeoffs
 * **Processes native resolutions up to 512×512** with intelligent patch-based handling for larger inputs
 ## 🏃 How to run LFM2-VL
+You can run LFM2-VL with Hugging Face [`transformers`](https://github.com/huggingface/transformers) via installing Transformers from source as follows:
 ```bash
+pip install git+https://github.com/huggingface/transformers.git@2e67a9b602a8aa5fcf9f82e25b4e331f3328976c pillow
 ```
 Here is an example of how to generate an answer with transformers in Python: