Instructions to use meta-llama/Llama-4-Scout-17B-16E with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-4-Scout-17B-16E with Transformers:

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

pipe = pipeline("image-text-to-text", model="meta-llama/Llama-4-Scout-17B-16E")
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("meta-llama/Llama-4-Scout-17B-16E")
model = AutoModelForMultimodalLM.from_pretrained("meta-llama/Llama-4-Scout-17B-16E")
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 meta-llama/Llama-4-Scout-17B-16E with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Llama-4-Scout-17B-16E"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-4-Scout-17B-16E",
		"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/meta-llama/Llama-4-Scout-17B-16E

SGLang

How to use meta-llama/Llama-4-Scout-17B-16E 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 "meta-llama/Llama-4-Scout-17B-16E" \
    --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": "meta-llama/Llama-4-Scout-17B-16E",
		"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 "meta-llama/Llama-4-Scout-17B-16E" \
        --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": "meta-llama/Llama-4-Scout-17B-16E",
		"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 meta-llama/Llama-4-Scout-17B-16E with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-4-Scout-17B-16E
```

Access rejected

#18

by sruthikesh - opened Apr 5, 2025

Discussion

sruthikesh

Apr 5, 2025

Hi, I've requested access and it was rejected. what is the reason for the reject?
Anyone else ran into this?

Taru2828sharma

Apr 5, 2025

same i am facing this issue also

bwalid13

Apr 6, 2025

I'm finding it frustrating that I'm not receiving a response regarding the reason for the refusal of access to models 3.1, 3.2, 3.3, and 4. As an independent researcher/developer, I was expecting a more straightforward process. I simply provided my first and last name in the form as requested, and I'm certain I didn't make any mistakes. It's disappointing to be left without any feedback or explanation. Furthermore, I don't see a way to resubmit my request or correct any potential errors. It's worth noting that I do have access to the models on the Meta website, but using Hugging Face is more convenient for installation and integration into my projects. Could you please provide some insight into what might have gone wrong? I'm looking forward to understanding the issue and potentially resolving it.

Akide

Apr 6, 2025

Got the problem that the request access has been rejected. i have successfully managed to apply 1-3 LLAMA series but was rejected by LLAMA 4 without any explanation.

shaunclimbon

Apr 7, 2025

Ditto. Have access to multiple previous versions but was rejected for Llama 4. Have no idea why and have no idea how to resolve. Anybody know of an up-to-date script to convert the Meta checkpoints (.pth) to HF format (.safetensors)?

ohhan777

Apr 8, 2025

I was rejected without any explanation. My colleague sitting next to me got approved right away.
Is there any way I can reapply?

MrDevolver

Apr 8, 2025

I was rejected without any explanation. My colleague sitting next to me got approved right away.
Is there any way I can reapply?

Lol, it's like in one of those movie scenes where the security guy lets in pretty girls, but then a bunch of guys he doesn't like show up and he instantly goes from: 🥰 to: 😡 and is like "Stop right there, you're not cool enough for this club!"

ankits0052

Jun 19, 2025

Same here I am also rejected and unable to find any issue with the form submitted.

Gowthamming

Aug 22, 2025

Hey all, read this discussion: https://huggingface.co/meta-llama/Meta-Llama-3-8B/discussions/124

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment