Instructions to use OpenGVLab/InternVL3-2B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL3-2B-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-2B-Instruct", 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/InternVL3-2B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL3-2B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL3-2B-Instruct"
# 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/InternVL3-2B-Instruct",
		"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/InternVL3-2B-Instruct

SGLang

How to use OpenGVLab/InternVL3-2B-Instruct 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/InternVL3-2B-Instruct" \
    --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/InternVL3-2B-Instruct",
		"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/InternVL3-2B-Instruct" \
        --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/InternVL3-2B-Instruct",
		"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/InternVL3-2B-Instruct with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL3-2B-Instruct
```

Update Quantization Method to BitsAndBytesConfig method for newer transformers version (locally, 4.53.1)

by SidTheChillGuy - opened Jul 9, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-4

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -195,14 +195,15 @@ model = AutoModel.from_pretrained(
 ```python
 import torch
-from transformers import AutoTokenizer, AutoModel
 path = "OpenGVLab/InternVL3-2B"
 model = AutoModel.from_pretrained(
     path,
     torch_dtype=torch.bfloat16,
-    load_in_8bit=True,
     low_cpu_mem_usage=True,
     use_flash_attn=True,
     trust_remote_code=True).eval()
 ```
@@ -262,7 +263,7 @@ import torchvision.transforms as T
 from decord import VideoReader, cpu
 from PIL import Image
 from torchvision.transforms.functional import InterpolationMode
-from transformers import AutoModel, AutoTokenizer
 IMAGENET_MEAN = (0.485, 0.456, 0.406)
 IMAGENET_STD = (0.229, 0.224, 0.225)
@@ -368,10 +369,11 @@ def split_model(model_name):
 # If you set `load_in_8bit=False`, you will need at least three 80GB GPUs.
 path = 'OpenGVLab/InternVL3-2B'
 device_map = split_model('InternVL3-2B')
 model = AutoModel.from_pretrained(
     path,
     torch_dtype=torch.bfloat16,
-    load_in_8bit=False,
     low_cpu_mem_usage=True,
     use_flash_attn=True,
     trust_remote_code=True,

 ```python
 import torch
+from transformers import AutoTokenizer, AutoModel, BitsAndBytesConfig
 path = "OpenGVLab/InternVL3-2B"
+quant_config = BitsAndBytesConfig(load_in_8bit=True)
 model = AutoModel.from_pretrained(
     path,
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
     use_flash_attn=True,
+    quantization_config = quant_config,
     trust_remote_code=True).eval()
 ```
 from decord import VideoReader, cpu
 from PIL import Image
 from torchvision.transforms.functional import InterpolationMode
+from transformers import AutoModel, AutoTokenizer, BitsAndBytesConfig
 IMAGENET_MEAN = (0.485, 0.456, 0.406)
 IMAGENET_STD = (0.229, 0.224, 0.225)
 # If you set `load_in_8bit=False`, you will need at least three 80GB GPUs.
 path = 'OpenGVLab/InternVL3-2B'
 device_map = split_model('InternVL3-2B')
+quant_config = BitsAndBytesConfig(load_in_8bit=False)
 model = AutoModel.from_pretrained(
     path,
     torch_dtype=torch.bfloat16,
+    quantization_config = quant_config,
     low_cpu_mem_usage=True,
     use_flash_attn=True,
     trust_remote_code=True,