Instructions to use nvidia/Nemotron-Elastic-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Nemotron-Elastic-12B with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Nemotron-Elastic-12B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/Nemotron-Elastic-12B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-Elastic-12B", trust_remote_code=True)
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nvidia/Nemotron-Elastic-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Nemotron-Elastic-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Nemotron-Elastic-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Nemotron-Elastic-12B

SGLang

How to use nvidia/Nemotron-Elastic-12B 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 "nvidia/Nemotron-Elastic-12B" \
    --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": "nvidia/Nemotron-Elastic-12B",
		"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 "nvidia/Nemotron-Elastic-12B" \
        --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": "nvidia/Nemotron-Elastic-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Nemotron-Elastic-12B with Docker Model Runner:
```
docker model run hf.co/nvidia/Nemotron-Elastic-12B
```

how long do you take to approve?

by jo987654321 - opened Nov 25, 2025

Discussion

jo987654321

Nov 25, 2025

Dear All, I submitted my request yesterday to evaluate this models capacity and yet no response from anyone?

Tibbnak

19 days ago

allegedly you could use the slicing script on the 30b repo and this guide to carve the 12b out of it yourself,

https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16#zero-shot-slicing-before-deployment

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