Instructions to use OPPOer/AndesVL-4B-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OPPOer/AndesVL-4B-Thinking with Transformers:

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

pipe = pipeline("image-text-to-text", model="OPPOer/AndesVL-4B-Thinking", 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("OPPOer/AndesVL-4B-Thinking", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OPPOer/AndesVL-4B-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OPPOer/AndesVL-4B-Thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OPPOer/AndesVL-4B-Thinking",
		"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/OPPOer/AndesVL-4B-Thinking

SGLang

How to use OPPOer/AndesVL-4B-Thinking 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 "OPPOer/AndesVL-4B-Thinking" \
    --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": "OPPOer/AndesVL-4B-Thinking",
		"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 "OPPOer/AndesVL-4B-Thinking" \
        --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": "OPPOer/AndesVL-4B-Thinking",
		"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 OPPOer/AndesVL-4B-Thinking with Docker Model Runner:
```
docker model run hf.co/OPPOer/AndesVL-4B-Thinking
```

Improve model card: Add metadata, paper, and GitHub links

by nielsr HF Staff - opened Oct 15, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

Files changed (1) hide show

README.md +9 -2

README.md CHANGED Viewed

@@ -1,8 +1,15 @@
 ---
 license: apache-2.0
 ---
 # AndesVL-4B-Thinking
-AndesVL is a suite of mobile-optimized Multimodal Large Language Models (MLLMs) with **0.6B to 4B parameters**, built upon Qwen3's LLM and various visual encoders. Designed for efficient edge deployment, it achieves first-tier performance on diverse benchmarks, including those for text-rich tasks, reasoning tasks, Visual Question Answering (VQA), multi-image tasks, multilingual tasks, and GUI tasks. Its "1+N" LoRA architecture and QALFT framework facilitate efficient task adaptation and model compression, enabling a 6.7x peak decoding speedup and a 1.8 bits-per-weight compression ratio on mobile chips.
 Detailed model sizes and components are provided below:
@@ -61,4 +68,4 @@ If you find our work helpful, feel free to give us a cite.
 ```
 # Acknowledge
-We are very grateful for the efforts of the [Qwen](https://huggingface.co/Qwen), [AimV2](https://huggingface.co/apple/aimv2-large-patch14-224) and [Siglip 2](https://arxiv.org/abs/2502.14786) projects.

 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
 ---
 # AndesVL-4B-Thinking
+This repository hosts the AndesVL-4B-Thinking model, presented in the paper [AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model](https://huggingface.co/papers/2510.11496).
+For the associated evaluation toolkit and code, see the [GitHub repository](https://github.com/OPPO-Mente-Lab/AndesVL_Evaluation).
+AndesVL is a suite of mobile-optimized Multimodal Large Language Models (MLLMs) with **0.6B to 4B parameters**, built upon Qwen3's LLM and various visual encoders. Designed for efficient edge deployment, it achieves first-tier performance across a wide range of open-source benchmarks, including fields such as text-rich image understanding, reasoning and math, multi-image comprehension, general VQA, hallucination mitigation, multilingual understanding, and GUI-related tasks when compared with state-of-the-art models of a similar scale.
 Detailed model sizes and components are provided below:
 ```
 # Acknowledge
+We are very grateful for the efforts of the [Qwen](https://huggingface.co/Qwen), [AimV2](https://huggingface.co/apple/aimv2-large-patch14-224) and [Siglip 2](https://arxiv.org/abs/2502.14786) projects.