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, device_map="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
```

Will it support MLX?

by neil0306 - opened Dec 13, 2025

Discussion

neil0306

Dec 13, 2025

Dear developers,

Thank you very much for releasing such a great model !!

Since the M4 Mac mini is very good, I hope to deploy such a great model on the Mac mini as well.
I would like to ask if there are any plans to support the MLX acceleration engine?

Thanks a lot !

hanxiao

Jina AI org Dec 15, 2025

done here:

neil0306

Dec 16, 2025

done here:

Thank you so much !!

Btw, I found that this model may not have been quantized, as it seems to consume nearly 40G of RAM.

Will there be a quantized version released later? For example, 4-bit, 8-bit quantization.

Best Wishes.

gmastrapas

Jina AI org Dec 16, 2025

•

edited Dec 16, 2025

Yes, we will probably do that once we have ironed out the details on vLLM support

neil0306

Dec 16, 2025

Yes, we will probably do that once we have ironed out the details on vLLM support

wow, thanks!
Just can't wait to see it !

hanxiao

Jina AI org Dec 16, 2025

okay fixed, so now model size is down to 2gb with mixed precision, details here

Language Model: 5.84 bits/weight (4-bit linear + float16 embeddings)
Vision Encoder: 7.95 bits/weight (4-bit where possible + float16)
VL Connector: 4.00 bits/weight (fully 4-bit)

pushing pr here, once its merged we should be able to use it directly via lmstudio etc on macos.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment