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
```

Running Llama-3_3-Nemotron-Super-49B-v1_5 on DGX Spark with NGC vLLM Container

#13

by PhotosGrafus - opened Dec 19, 2025

Discussion

PhotosGrafus

Dec 19, 2025

Running Llama-3_3-Nemotron-Super-49B-v1_5 on DGX Spark with NGC vLLM Container

Hardware

System: NVIDIA DGX Spark
Memory: 128GB unified memory (CPU+GPU shared)
GPU: Single GPU (Grace Blackwell architecture)
Current working model: gpt-oss-120b runs successfully with NGC vLLM container

Current Setup

I'm using the NGC vLLM container for inference:

nvcr.io/nvidia/vllm:25.11-py3  (vLLM 0.11.0)

My working gpt-oss-120b configuration:

sudo docker run -d \
    --gpus all \
    --ipc=host \
    --shm-size 32g \
    -v /home/data/models/gpt-oss-120b:/model \
    -p 8000:8000 \
    nvcr.io/nvidia/vllm:25.11-py3 \
    vllm serve /model \
    --host 0.0.0.0 \
    --port 8000 \
    --gpu-memory-utilization 0.7 \
    --max-model-len 131072 \
    --trust-remote-code \
    --generation-config=vllm

Questions

The HuggingFace example uses pip install vllm==0.9.2 with tensor-parallel-size=8. I need to adapt this for DGX Spark (single GPU, unified memory).

1. NGC vLLM 0.11.0 Compatibility

Is nvcr.io/nvidia/vllm:25.11-py3 (vLLM 0.11.0) compatible with this model?
Or must I use vllm==0.9.2 specifically?

2. Required Parameters
Please confirm or correct each parameter for DGX Spark:

Parameter	My assumption	Correct?
`--trust-remote-code`	Required	?
`--enforce-eager`	Required	?
`--gpu-memory-utilization`	0.7 (unified memory constraint)	?
`--max-model-len`	32768 or 65536?	?
`--tensor-parallel-size`	1 (single GPU)	?
`--generation-config`	vllm	?

3. DeciLMForCausalLM Architecture

I saw GitHub issues about DeciLMForCausalLM not being supported in some vLLM versions
Does NGC vLLM 0.11.0 support this architecture natively, or does --trust-remote-code handle it?

4. Reasoning Mode

Does vLLM deployment support <think> tag parsing natively?
Or is additional configuration needed for reasoning on/off modes?

5. Complete Docker Command
If possible, please provide a tested docker run command for DGX Spark with:

NGC vLLM container (or specify if pip version is required)
Single GPU / unified memory configuration
Recommended context length for 128GB unified memory

Model Location

/home/data/models/llama-nemotron-super-49b/

(Downloaded via huggingface-cli download nvidia/Llama-3_3-Nemotron-Super-49B-v1_5)

Thank you for any guidance. I want to avoid trial-and-error on production hardware.

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