Instructions to use McGill-NLP/A3-Qwen3.5-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use McGill-NLP/A3-Qwen3.5-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="McGill-NLP/A3-Qwen3.5-4B")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("McGill-NLP/A3-Qwen3.5-4B")
model = AutoModelForMultimodalLM.from_pretrained("McGill-NLP/A3-Qwen3.5-4B", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use McGill-NLP/A3-Qwen3.5-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "McGill-NLP/A3-Qwen3.5-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "McGill-NLP/A3-Qwen3.5-4B",
		"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/McGill-NLP/A3-Qwen3.5-4B

SGLang

How to use McGill-NLP/A3-Qwen3.5-4B 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 "McGill-NLP/A3-Qwen3.5-4B" \
    --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": "McGill-NLP/A3-Qwen3.5-4B",
		"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 "McGill-NLP/A3-Qwen3.5-4B" \
        --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": "McGill-NLP/A3-Qwen3.5-4B",
		"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 McGill-NLP/A3-Qwen3.5-4B with Docker Model Runner:
```
docker model run hf.co/McGill-NLP/A3-Qwen3.5-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A3-Qwen3.5-4B

💾 Code	📄 Paper	🌐 Website
🤗 Dataset	🤖 Models	📦 PyPI

Structured Distillation of Web Agent Capabilities Enables Generalization

Xing Han Lù, Siva Reddy

A3-Qwen3.5-4B is a 4B web agent fine-tuned from Qwen/Qwen3.5-4B on A3-Synth.

This model was developed using the Agent-as-Annotators (A3) framework, which structures synthetic trajectory generation for web agents by analogy to human annotation roles, replacing the Task Designer, Annotator, and Supervisor with modular LLM components. See A3-Qwen3.5-9B for full details on the framework performance and methodology.

Quick Start: Evaluation

To evaluate the model using the official framework, first install the package:

pip install agent-as-annotators

Then, you can serve the model and run evaluation:

# 1. Serve the model (e.g. using vLLM)
vllm serve --model McGill-NLP/A3-Qwen3.5-4B

# 2. Run evaluation on a benchmark
a3-eval --benchmark webarena_test --model A3-qwen3.5-4b

Citation

@misc{lu2026structured,
      title={Structured Distillation of Web Agent Capabilities Enables Generalization}, 
      author={Xing Han Lù and Siva Reddy},
      year={2026},
      eprint={2604.07776},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}