Instructions to use pinkelephantlimited/pink-elephant-vlm-nested with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pinkelephantlimited/pink-elephant-vlm-nested with Transformers:

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

pipe = pipeline("image-text-to-text", model="pinkelephantlimited/pink-elephant-vlm-nested")
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("pinkelephantlimited/pink-elephant-vlm-nested")
model = AutoModelForMultimodalLM.from_pretrained("pinkelephantlimited/pink-elephant-vlm-nested", 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 pinkelephantlimited/pink-elephant-vlm-nested with vLLM:

Install from pip and serve model

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

SGLang

How to use pinkelephantlimited/pink-elephant-vlm-nested 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 "pinkelephantlimited/pink-elephant-vlm-nested" \
    --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": "pinkelephantlimited/pink-elephant-vlm-nested",
		"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 "pinkelephantlimited/pink-elephant-vlm-nested" \
        --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": "pinkelephantlimited/pink-elephant-vlm-nested",
		"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 pinkelephantlimited/pink-elephant-vlm-nested with Docker Model Runner:
```
docker model run hf.co/pinkelephantlimited/pink-elephant-vlm-nested
```

Pink Elephant VLM (nested-quantized)

An efficient vision-language model by Pink Elephant Limited (Hong Kong), released as a nested-quantized variant for on-device deployment. Handles image understanding, document reading, and multilingual visual question answering.

Built as the base vision-language model for the Pink Elephant Talk product line. The fine-tuned daily-helper release is available as pink-elephant-talk-vlm-3b with a GGUF quantized version in pink-elephant-talk-vlm-3b-gguf.

License: this model redistributes Qwen2.5-VL weights under the Qwen RESEARCH LICENSE AGREEMENT (see the LICENSE file in this repository). "Qwen" is a trademark of Alibaba Group.

About the company

Pink Elephant Limited is a commercial AI technology development company registered in Hong Kong. It builds private, on-device AI products: every model runs on the phone's own hardware and no user data leaves the device.

Downloads last month: 79

Safetensors

Model size

4B params

Tensor type

BF16