Instructions to use AIDC-AI/Ovis2.5-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIDC-AI/Ovis2.5-9B with Transformers:

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

pipe = pipeline("image-text-to-text", model="AIDC-AI/Ovis2.5-9B", 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("AIDC-AI/Ovis2.5-9B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AIDC-AI/Ovis2.5-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AIDC-AI/Ovis2.5-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIDC-AI/Ovis2.5-9B",
		"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/AIDC-AI/Ovis2.5-9B

SGLang

How to use AIDC-AI/Ovis2.5-9B 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 "AIDC-AI/Ovis2.5-9B" \
    --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": "AIDC-AI/Ovis2.5-9B",
		"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 "AIDC-AI/Ovis2.5-9B" \
        --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": "AIDC-AI/Ovis2.5-9B",
		"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 AIDC-AI/Ovis2.5-9B with Docker Model Runner:
```
docker model run hf.co/AIDC-AI/Ovis2.5-9B
```

How can we run this model on mac OS or any machine that does not have GPU?

by merhanjan - opened Aug 22, 2025

Discussion

merhanjan

Aug 22, 2025

I am trying to run this model on my Mac, but I cannot install flash_attn because the machine does not have a GPU.

ThetaCursed

Aug 22, 2025

Without flash attention, you won't be able to run the model, since in the custom model code this is a necessary import.

I run it without problems on RTX A6000, it's very cheap on all sorts of Cloud GPUs

xxyyy123

AIDC-AI org Aug 23, 2025

Hi, we’ve added SDPA support in the code, so it can now run without flash-attention.

merhanjan

Aug 24, 2025

Hi, we’ve added SDPA support in the code, so it can now run without flash-attention.

Thanks for the update, shall I do anything in my code?

merhanjan

Aug 24, 2025

I think there is something wrong with this mode. Even the Google Colab example you provided does not work and throws an error. Loading the model directly without the transformer also throws an error.

stoefln

Aug 24, 2025

Can someone recommend a way to run this cost-efficiently?

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