Instructions to use nvidia/Nemotron-Cascade-2-30B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Nemotron-Cascade-2-30B-A3B with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Nemotron-Cascade-2-30B-A3B", trust_remote_code=True)
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-2-30B-A3B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-Cascade-2-30B-A3B", trust_remote_code=True, 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Nemotron-Cascade-2-30B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Nemotron-Cascade-2-30B-A3B"
# 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-2-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Nemotron-Cascade-2-30B-A3B

SGLang

How to use nvidia/Nemotron-Cascade-2-30B-A3B 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-2-30B-A3B" \
    --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-2-30B-A3B",
		"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-2-30B-A3B" \
        --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-2-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Nemotron-Cascade-2-30B-A3B with Docker Model Runner:
```
docker model run hf.co/nvidia/Nemotron-Cascade-2-30B-A3B
```

Add HMMT February 2026 evaluation results (avg@8)

#30

by bogoconic1 - opened 15 days ago

base: refs/heads/main

←

from: refs/pr/30

Discussion Files changed

-0

bogoconic1

15 days ago

•

edited 15 days ago

Adds a community evaluation result for HMMT February 2026: 81.06% avg@8 (214/264 correct).

Evaluated all 33 problems from MathArena/hmmt_feb_2026, with 8 independently sampled responses per problem.

Evaluation settings:

Model: original BF16 checkpoint, without quantization.
Inference: vLLM 0.23.0 on 8× NVIDIA H200, with FP32 Mamba SSM cache.
Generation: thinking enabled, temperature 1.0, top-p 1.0, maximum 131,072 output tokens per response.
Tools: none.

System prompt:

You are a helpful and harmless assistant.

You are not allowed to use any tools.

User prompt:

{problem}

Please place your final answer inside \boxed{}.

Grading used math-verify==0.9.0 on the last boxed answer after </think>.

This is an independent community evaluation using the MathArena dataset.

Add HMMT February 2026 evaluation results (avg@8)c7ff875d

bogoconic1 changed pull request status to open 15 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment