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
```

s-jse commited on about 13 hours ago

Commit

da10385

verified ·

1 Parent(s): f83d2b0

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -1470,6 +1470,8 @@ Across 62 vision benchmarks, LFM3-VL-2B scores at least 8 points ahead of all mo
 <p><small>All scores are normalized to a 0–100 scale. Each category score is the unweighted mean of its benchmark scores, and the Average row is the unweighted mean across all 62 benchmarks.</small></p>
 <p><small>
 <strong>Original score scales:</strong> MME uses a 0–2800 scale; OCRBench, 0–1000; and DocVQA and InfographicVQA, 0–1.<br>
 <strong>RefCOCO-avg:</strong> Mean P@1 across eight splits: RefCOCO (val, testA, testB), RefCOCO+ (val, testA, testB), and RefCOCOg (val, test).<br>

 <p><small>All scores are normalized to a 0–100 scale. Each category score is the unweighted mean of its benchmark scores, and the Average row is the unweighted mean across all 62 benchmarks.</small></p>
+<p><small>We used GPT-6 Luna as a judge for benchmarks that require an LLM judge.</small></p>
 <p><small>
 <strong>Original score scales:</strong> MME uses a 0–2800 scale; OCRBench, 0–1000; and DocVQA and InfographicVQA, 0–1.<br>
 <strong>RefCOCO-avg:</strong> Mean P@1 across eight splits: RefCOCO (val, testA, testB), RefCOCO+ (val, testA, testB), and RefCOCOg (val, test).<br>