Instructions to use nvidia/Nemotron-H-47B-Reasoning-128K-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Nemotron-H-47B-Reasoning-128K-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Nemotron-H-47B-Reasoning-128K-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nvidia/Nemotron-H-47B-Reasoning-128K-FP8", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Nemotron-H-47B-Reasoning-128K-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Nemotron-H-47B-Reasoning-128K-FP8"
# 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-H-47B-Reasoning-128K-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Nemotron-H-47B-Reasoning-128K-FP8

SGLang

How to use nvidia/Nemotron-H-47B-Reasoning-128K-FP8 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-H-47B-Reasoning-128K-FP8" \
    --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-H-47B-Reasoning-128K-FP8",
		"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-H-47B-Reasoning-128K-FP8" \
        --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-H-47B-Reasoning-128K-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Nemotron-H-47B-Reasoning-128K-FP8 with Docker Model Runner:
```
docker model run hf.co/nvidia/Nemotron-H-47B-Reasoning-128K-FP8
```

Value error, The checkpoint you are trying to load has model type `nemotron_h` but Transformers does not recognize this architecture.

by kshinoda - opened Jun 28, 2025

Discussion

kshinoda

Jun 28, 2025

Thank you for your hard work to release such a great model!!

Unfortunately, the following error occurred when using this FP8 model with vllm.

Value error, The checkpoint you are trying to load has model type `nemotron_h` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

Even though I have updated transformers up to 4.52.4 following the error statement, the error can not be resolved.

Is this error due to the missing 'modeling_nemotron_h.py', which Nemotron-H-47B-Reasoning-128K (non-FP8 version) has?
I could successfully use Nemotron-H-47B-Reasoning-128K (non-FP8 version) with vllm.

This error occurred with the following environment.

vllm == 0.9.1
transformers == 4.52.4
CUDA == 12.6
torch == 2.7.0

Thank you for your support in advance.

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