Instructions to use nvidia/Nemotron-Cascade-14B-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Nemotron-Cascade-14B-Thinking with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Nemotron-Cascade-14B-Thinking")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/Nemotron-Cascade-14B-Thinking")
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-Cascade-14B-Thinking", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Nemotron-Cascade-14B-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Nemotron-Cascade-14B-Thinking"
# 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-Cascade-14B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Nemotron-Cascade-14B-Thinking

SGLang

How to use nvidia/Nemotron-Cascade-14B-Thinking 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-Cascade-14B-Thinking" \
    --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-Cascade-14B-Thinking",
		"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-Cascade-14B-Thinking" \
        --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-Cascade-14B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Nemotron-Cascade-14B-Thinking with Docker Model Runner:
```
docker model run hf.co/nvidia/Nemotron-Cascade-14B-Thinking
```

boxin-wbx commited on Dec 8, 2025

Commit

334ea35

verified ·

1 Parent(s): b42f335

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ tags:
 <img src="fig/nemotron-x-14b-thinking-results.png" alt="main_fig" style="width: 1000px; max-width: 100%;" />
-We're excited to introduce [Nemotron-*X*-14B-Thinking](https://huggingface.co/nvidia/Nemotron-X-14B-Thinking), a powerful general-purpose model trained through sequential and domain-wise reinforcement learning. Nemotron-*X*-14B-Thinking is post-trained from the [Qwen3-14B Base model](https://huggingface.co/Qwen/Qwen3-14B-Base), and it achieves best-in-class performance across a wide range of benchmarks. Different from [Nemotron-*X*-8B](https://huggingface.co/nvidia/Nemotron-X-8B), Nemotron-*X*-14B-Thinking is designed exclusively for the ***thinking*** mode.
 ## Training Pipeline
@@ -65,6 +65,10 @@ The training pipeline for Nemotron-*X* begins with a multi-stage SFT phase to eq
 | ***Tool Calling*** |
 | BFCL V3 | 70.4 | 67.9 | 68.6 | 67.5 |
 ## Chat Template

 <img src="fig/nemotron-x-14b-thinking-results.png" alt="main_fig" style="width: 1000px; max-width: 100%;" />
+We're excited to introduce [Nemotron-*X*-14B-Thinking](https://huggingface.co/nvidia/Nemotron-X-14B-Thinking), a powerful general-purpose model trained through sequential and domain-wise reinforcement learning. Nemotron-*X*-14B-Thinking is post-trained from the [Qwen3-14B Base](https://huggingface.co/Qwen/Qwen3-14B-Base) model, and it achieves best-in-class performance across a wide range of benchmarks. Different from [Nemotron-*X*-8B](https://huggingface.co/nvidia/Nemotron-X-8B), Nemotron-*X*-14B-Thinking is designed exclusively for the ***thinking*** mode.
 ## Training Pipeline
 | ***Tool Calling*** |
 | BFCL V3 | 70.4 | 67.9 | 68.6 | 67.5 |
+## Evaluation Tookit
+To reproduce our results, please check evaluation code, scripts, cached prediction files in https://huggingface.co/nvidia/Nemotron-X-14B-Thinking/blob/main/evaluation/README.md
 ## Chat Template