Instructions to use OpenGVLab/InternVL3_5-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL3_5-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3_5-8B", 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 AutoModel
model = AutoModel.from_pretrained("OpenGVLab/InternVL3_5-8B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL3_5-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL3_5-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL3_5-8B",
		"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/OpenGVLab/InternVL3_5-8B

SGLang

How to use OpenGVLab/InternVL3_5-8B 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 "OpenGVLab/InternVL3_5-8B" \
    --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": "OpenGVLab/InternVL3_5-8B",
		"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 "OpenGVLab/InternVL3_5-8B" \
        --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": "OpenGVLab/InternVL3_5-8B",
		"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 OpenGVLab/InternVL3_5-8B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL3_5-8B
```

what is the recommended method to start up the vllm server engine for inferencing for InternVL3_5-8B, getting 2 qps?

by Rupasai - opened Sep 9, 2025

Discussion

Rupasai

Sep 9, 2025

•

edited Sep 9, 2025

I am using VLLM library for inference. For some strange reason I am getting qps around 2. Is this expected?. I am starting the server as follows:

vllm serve "model_path" --trust-remote-code --max-num-seqs 1000 --max-model-len 8192 --gpu-memory-utilization 0.95 --limit-mm-per-prompt '{"image": 1}' --tensor-parallel-size 1 --trust-remote-code --port 8080

Input: prompt + single image
Output: ~200 tokens
vllm version I am using: 10.1.1
gpu: H100

Kerlion

Sep 23, 2025

I run as blow command with only 48GB VRAM with quantization on the fly:
vllm serve //modles/InternVL3_5-38B
--served-model-name "InternVL3_5-38B"
--allowed-local-media-path /
--max-model-len 32K
--gpu-memory-utilization 0.9
--tensor-parallel-size 1
--quantization bitsandbytes
--trust-remote-code
--host 0.0.0.0
--port 8080

got below speed:
Avg prompt throughput: 119.4 tokens/s, Avg generation throughput: 23.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.9%, Prefix cache hit rate: 29.9%.

But my Linux box crashed with I changed tp=2 without quantization.

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