Instructions to use nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4", 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/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4"
# 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/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4

SGLang

How to use nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 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/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4" \
    --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/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4",
		"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/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4" \
        --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/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4
```

tomer-nv commited on Jul 2

Commit

c743c5e

1 Parent(s): f52cc60

Update model card details

Browse files

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -94,8 +94,8 @@ Global<br>
 ### Use Case: <br>
 NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 is a general purpose reasoning and chat model intended to be used in English, Code, and supported multilingual contexts. This model is optimized for collaborative agents and high-volume workloads. It is intended to be used by developers designing AI Agent systems, chatbots, RAG systems, and other AI-powered applications. This model is also suitable for complex instruction-following tasks and long-context reasoning.
-### Release Date [Insert the expected release date below]:  <br>
-June 12, 2026 via [Hugging Face](https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4)
 ## References(s):
 * [\[2411.19146\] Puzzle: Distillation-Based NAS for Inference-Optimized LLMs](https://arxiv.org/abs/2411.19146)
@@ -613,7 +613,8 @@ The GitHub Crawl was collected using the GitHub REST API and the Amazon S3 API.
 * **Labeling Method by dataset**: Hybrid: Automated, Human, Synthetic
 ## Inference:
-* **Acceleration Engine:** vLLM
 **Test Hardware:**
 - 1× NVIDIA H100-80GB
 - 8× NVIDIA H100-80GB

 ### Use Case: <br>
 NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 is a general purpose reasoning and chat model intended to be used in English, Code, and supported multilingual contexts. This model is optimized for collaborative agents and high-volume workloads. It is intended to be used by developers designing AI Agent systems, chatbots, RAG systems, and other AI-powered applications. This model is also suitable for complex instruction-following tasks and long-context reasoning.
+### Release Date:  <br>
+July 6, 2026 via [Hugging Face](https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4)
 ## References(s):
 * [\[2411.19146\] Puzzle: Distillation-Based NAS for Inference-Optimized LLMs](https://arxiv.org/abs/2411.19146)
 * **Labeling Method by dataset**: Hybrid: Automated, Human, Synthetic
 ## Inference:
+**Acceleration Engine:** vLLM
 **Test Hardware:**
 - 1× NVIDIA H100-80GB
 - 8× NVIDIA H100-80GB