Instructions to use nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", trust_remote_code=True, dtype="auto")

Inference
Local Apps Settings

vLLM

How to use nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5"
# 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/Llama-3_3-Nemotron-Super-49B-v1_5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5

SGLang

How to use nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 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/Llama-3_3-Nemotron-Super-49B-v1_5" \
    --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/Llama-3_3-Nemotron-Super-49B-v1_5",
		"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/Llama-3_3-Nemotron-Super-49B-v1_5" \
        --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/Llama-3_3-Nemotron-Super-49B-v1_5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 with Docker Model Runner:
```
docker model run hf.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
```

Possible to disable thinking via a karg?

by SuperbEmphasis - opened Sep 11, 2025

Discussion

SuperbEmphasis

Sep 11, 2025

I am testing out this model for a tool that adds it's own prompts. Unfortunately for some of the parts it does not parse the thinking tags correctly.

Is it possible to disable thinking in the API without having to add /no_think or the system prompt? Something like enable_thinking: False or something?

SuperbEmphasis

Sep 13, 2025

Actually after thinking about the models thinking.....

I think I can just change the chat template, and change the second line to set enable_thinking to false.... which is actually nice because /think should still work.

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