Instructions to use LiquidAI/LFM3-VL-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM3-VL-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="LiquidAI/LFM3-VL-2B", trust_remote_code=True)
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("LiquidAI/LFM3-VL-2B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LiquidAI/LFM3-VL-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM3-VL-2B"
# 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/LFM3-VL-2B",
		"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/LFM3-VL-2B

SGLang

How to use LiquidAI/LFM3-VL-2B 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/LFM3-VL-2B" \
    --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/LFM3-VL-2B",
		"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/LFM3-VL-2B" \
        --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/LFM3-VL-2B",
		"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/LFM3-VL-2B with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM3-VL-2B
```

samuelstevens commited on 5 days ago

Commit

2bce595

verified ·

1 Parent(s): b22858a

Inference table: add LM Studio to GGUF; neutral desktop app sentence

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -131,7 +131,7 @@ Choose a checkpoint variant for your inference framework and hardware.
 </tr>
 <tr style="border: 0;">
 <td style="border: 0; padding: 0.55em 0.75em;"><a href="https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF">GGUF</a></td>
-<td style="border: 0; padding: 0.55em 0.75em;"><a href="https://docs.liquid.ai/deployment/on-device/llama-cpp">llama.cpp</a></td>
 <td style="border: 0; padding: 0.55em 0.75em;">Local inference on CPUs and GPUs.</td>
 </tr>
 <tr style="border: 0;">
@@ -201,7 +201,7 @@ print(processor.batch_decode(generated_ids, skip_special_tokens=True)[0])
 <details>
 <summary><strong>On-device inference with llama.cpp</strong></summary>
-For most on-device use cases, we recommend [llama.cpp](https://github.com/ggml-org/llama.cpp) b11960 or newer with the [GGUF checkpoints](https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF). The fastest way to try it is [Llama.app](https://llama.app) for macOS and Windows: on the [GGUF page](https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF), click **Use this model → llama**.
 From a terminal, start a web chat UI and an OpenAI-compatible API at `http://localhost:8080`. With `-hf`, llama.cpp downloads the model and the matching vision projector (mmproj):

 </tr>
 <tr style="border: 0;">
 <td style="border: 0; padding: 0.55em 0.75em;"><a href="https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF">GGUF</a></td>
+<td style="border: 0; padding: 0.55em 0.75em;"><a href="https://docs.liquid.ai/deployment/on-device/llama-cpp">llama.cpp</a>, <a href="https://docs.liquid.ai/deployment/on-device/lm-studio">LM Studio</a></td>
 <td style="border: 0; padding: 0.55em 0.75em;">Local inference on CPUs and GPUs.</td>
 </tr>
 <tr style="border: 0;">
 <details>
 <summary><strong>On-device inference with llama.cpp</strong></summary>
+For most on-device use cases, we recommend [llama.cpp](https://github.com/ggml-org/llama.cpp) b11960 or newer with the [GGUF checkpoints](https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF). To run it in a desktop app such as [Llama.app](https://llama.app) or [LM Studio](https://lmstudio.ai), click **Use this model** on the [GGUF page](https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF) and pick the app.
 From a terminal, start a web chat UI and an OpenAI-compatible API at `http://localhost:8080`. With `-hf`, llama.cpp downloads the model and the matching vision projector (mmproj):