Instructions to use jinaai/jina-vlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jinaai/jina-vlm with Transformers:

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

pipe = pipeline("image-text-to-text", model="jinaai/jina-vlm", 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)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("jinaai/jina-vlm", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jinaai/jina-vlm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jinaai/jina-vlm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jinaai/jina-vlm",
		"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/jinaai/jina-vlm

SGLang

How to use jinaai/jina-vlm 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 "jinaai/jina-vlm" \
    --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": "jinaai/jina-vlm",
		"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 "jinaai/jina-vlm" \
        --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": "jinaai/jina-vlm",
		"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 jinaai/jina-vlm with Docker Model Runner:
```
docker model run hf.co/jinaai/jina-vlm
```

Georgios Mastrapas commited on Apr 2

Commit

ddfa80b

1 Parent(s): bd51ae6

chore: update arch graph

Browse files

Files changed (2) hide show

README.md +2 -2
assets/jvlm_architecture.png +2 -2

README.md CHANGED Viewed

@@ -54,7 +54,7 @@ inference: false
 [Blog](https://jina.ai/news/jina-vlm-small-multilingual-vision-language-model/) | API | AWS | Azure | GCP | [Arxiv](https://arxiv.org/abs/2512.04032)
-`jina-vlm` is a 2.4B parameter vision-language model that achieves state-of-the-art multilingual visual question answering among open 2B-scale VLMs. The model couples a SigLIP2 vision encoder with a Qwen3 language backbone through an attention-pooling connector that enables token-efficient processing of arbitrary-resolution images. Training data comprises approximately 5M multimodal samples and 12B text tokens across 29 languages, with roughly half in English and the remainder spanning high- and moderate-resource languages.
 ![jina-vlm architecture](./assets/jvlm_architecture.png)
@@ -993,4 +993,4 @@ If you find `jina-vlm` useful in your research, please cite our [technical repor
 ## License
-`jina-vlm` is licensed under CC BY-NC 4.0. For commercial usage inquiries, feel free to [contact us](https://jina.ai/contact-sales/).

 [Blog](https://jina.ai/news/jina-vlm-small-multilingual-vision-language-model/) | API | AWS | Azure | GCP | [Arxiv](https://arxiv.org/abs/2512.04032)
+`jina-vlm` is a token-efficient 2.4B parameter vision-language model that achieves state-of-the-art multilingual VQA performance among open 2B-scale VLMs. The model couples a SigLIP2 vision encoder with a Qwen3 language decoder and makes use of image tiling and attention-pooling for token-efficient processing of arbitrary-resolution images.
 ![jina-vlm architecture](./assets/jvlm_architecture.png)
 ## License
+`jina-vlm` is licensed under CC BY-NC 4.0. For commercial usage inquiries, feel free to [contact us](https://jina.ai/contact-sales/).

assets/jvlm_architecture.png CHANGED Viewed

Git LFS Details

SHA256: 8941f6788e95e12904ac301bff2f37089a1b2421e2c44c4cffa1743a62a3915e
Pointer size: 131 Bytes
Size of remote file: 248 kB

Git LFS Details

SHA256: 6a336b7e3eda7a97ffbd2d1b79e6d0eeafc2320157027a7cec21a132adfbd707
Pointer size: 132 Bytes
Size of remote file: 2.84 MB