Instructions to use meta-llama/Llama-3.2-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-3.2-3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Llama-3.2-3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/Llama-3.2-3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Llama-3.2-3B-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": "meta-llama/Llama-3.2-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-3.2-3B-Instruct

SGLang

How to use meta-llama/Llama-3.2-3B-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 "meta-llama/Llama-3.2-3B-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": "meta-llama/Llama-3.2-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-3.2-3B-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": "meta-llama/Llama-3.2-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meta-llama/Llama-3.2-3B-Instruct with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-3.2-3B-Instruct
```

Meta Llama 3 Access Request Stuck in Pending for 8+ Days — Need Reset to Apply Under Organization (If that is the issue)

#236

by TandemOS - opened Nov 19, 2025

Discussion

TandemOS

Nov 19, 2025

Hi HF Team,

Our access request for Meta Llama 3 (8B-Instruct) has been stuck in Pending for over 8 days.

Details:

Personal account: TandemOS

Organization: Tandem

Request was submitted under my org account, but might be tied to my personal account. We need the access under our organization.

The issue:

The request does not appear under the org-level “Gated Repos,” only under my personal “TandemOS.”

The model card will not let us cancel, resubmit, or reapply under the org.

The “Use this model” button is still blocked, and we cannot proceed with fine-tuning.

This is blocking production training for our team.

Can you please:

Either approve the existing request, OR

Reset / cancel the pending request so we can re-submit under the Tandem org.

Happy to provide any info needed.
Thanks so much for your help!

Dylan
Co-founder @ Tandem

TandemOS

Dec 2, 2025

Hi @meta-llama team,

My access request for Meta-Llama-3-8B-Instruct has been stuck in “Pending” since November 11 (21+ days). This is blocking a production ML pipeline for my company’s AI design platform, and Hugging Face support confirmed that approvals are entirely handled by Meta.

Could you please review and approve (or reset) this request?

HF Username: tandemOS
Model: meta-llama/Meta-Llama-3-8B-Instruct
Status: Pending since Nov 11

This is time-sensitive for us — any help would be deeply appreciated.

Thank you.

TandemOS

Dec 2, 2025

@meta

TandemOS

Dec 2, 2025

@meta-llama

TandemOS

Dec 2, 2025

@meta-llama-bot

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