Instructions to use zenlm/zen-vl-30b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zenlm/zen-vl-30b-instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="zenlm/zen-vl-30b-instruct")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("zenlm/zen-vl-30b-instruct")
model = AutoModelForImageTextToText.from_pretrained("zenlm/zen-vl-30b-instruct")
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

vLLM

How to use zenlm/zen-vl-30b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zenlm/zen-vl-30b-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": "zenlm/zen-vl-30b-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/zenlm/zen-vl-30b-instruct

SGLang

How to use zenlm/zen-vl-30b-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 "zenlm/zen-vl-30b-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": "zenlm/zen-vl-30b-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 "zenlm/zen-vl-30b-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": "zenlm/zen-vl-30b-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 zenlm/zen-vl-30b-instruct with Docker Model Runner:
```
docker model run hf.co/zenlm/zen-vl-30b-instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Zen Vl 30B Instruct

Zen VL 30B Instruct - Frontier vision-language model with Zen identity (31B MoE)

Model Details

Architecture: Zen
Parameters: 30B
Context Window: 256K tokens (expandable to 1M)
License: Apache 2.0
Training: Fine-tuned with Zen identity and instruction following

Capabilities

🎨 Visual Understanding: Image analysis, video comprehension, spatial reasoning
📝 OCR: Text extraction in 32 languages
🧠 Multimodal Reasoning: STEM, math, code generation

Usage

from transformers import AutoModelForVision2Seq, AutoProcessor
from PIL import Image

# Load model
model = AutoModelForVision2Seq.from_pretrained(
    "zenlm/zen-vl-30b-instruct",
    device_map="auto"
)
processor = AutoProcessor.from_pretrained("zenlm/zen-vl-30b-instruct")

# Process image
image = Image.open("example.jpg")
prompt = "What's in this image?"

messages = [{"role": "user", "content": prompt}]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=text, images=image, return_tensors="pt").to(model.device)

# Generate
outputs = model.generate(**inputs, max_new_tokens=256)
response = processor.decode(outputs[0], skip_special_tokens=True)
print(response)

Citation

@misc{zenvl2025,
  title={Zen VL: Vision-Language Models with Integrated Function Calling},
  author={Hanzo AI Team},
  year={2025},
  publisher={Zen Language Models},
  url={https://github.com/zenlm/zen-vl}
}

License

Apache 2.0

Created by Hanzo AI for the Zen model family.

Downloads last month: 8

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for zenlm/zen-vl-30b-instruct

Unable to build the model tree, the base model loops to the model itself. Learn more.

zenlm
/

zen-vl-30b-instruct