Instructions to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-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-3-Super-120B-A12B-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-3-Super-120B-A12B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4

SGLang

How to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-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-3-Super-120B-A12B-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-3-Super-120B-A12B-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-3-Super-120B-A12B-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-3-Super-120B-A12B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4
```

nemotron120b

#31

by willowoods - opened May 8

base: refs/heads/main

←

from: refs/pr/31

Discussion Files changed

-6

This PR is in draft mode

Files changed (1) hide show

README.md +3 -6

README.md CHANGED Viewed

@@ -69,7 +69,6 @@ track_downloads: true
 | **Supported Languages** | English, French, German, Italian, Japanese, Spanish, Chinese |
 | **Best For** | Agentic workflows, long-context reasoning, high-volume workloads (e.g. IT ticket automation), tool use, RAG |
 | **Reasoning Mode** | Configurable on/off via chat template (`enable_thinking=True/False`) |
-| **Speculative Decoding** | Includes a built-in MTP head, with an updated MTPv2 head available as a separate [checkpoint](https://huggingface.co/nvidia/Nemotron-3-Super-120B-A12B-BF16-MTPv2) |
 | **License** | [NVIDIA Nemotron Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/) |
 | **Release Date** | March 11, 2026 |
@@ -272,7 +271,7 @@ vllm serve $MODEL_CKPT \
 ##### vLLM on DGX Spark
-To deploy the NVFP4 chekpoint on NVIDIA DGX Spark, make sure that you are using the `vllm/vllm-openai:v0.27.1` container image and use the following command:
 ```bash
 docker run --rm -it --gpus all \
@@ -284,7 +283,7 @@ docker run --rm -it --gpus all \
   -v ~/.cache/huggingface:/root/.cache/huggingface \
   -v $(pwd)/super_v3_reasoning_parser.py:/app/super_v3_reasoning_parser.py \
   -p 8000:8000 \
-  vllm/vllm-openai:v0.27.1 \
     --model nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 \
     --served-model-name nvidia/nemotron-3-super \
     --host 0.0.0.0 \
@@ -303,7 +302,7 @@ docker run --rm -it --gpus all \
     --moe-backend marlin \
     --mamba_ssm_cache_dtype float16 \
     --quantization fp4 \
-    --speculative_config '{"method":"mtp","num_speculative_tokens":3,"model":"nvidia/Nemotron-3-Super-120B-A12B-BF16-MTPv2","moe_backend":"triton"}' \
     --reasoning-parser-plugin /app/super_v3_reasoning_parser.py \
     --reasoning-parser super_v3 \
     --enable-auto-tool-choice \
@@ -617,8 +616,6 @@ Alongside the model, we release our final pre-training and post-training data, a
 More details on the datasets and synthetic data generation methods can be found in the technical report _[**_NVIDIA Nemotron 3 Super_**](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Super-Technical-Report.pdf)_.
-For more information about the datasets used to train this model, please see the [Public Summary of Training Content](https://developer.download.nvidia.com/assets/nemo/docs/public-summary-of-training-content-for-nvidia-nemotron.pdf)
 <details>
 <summary><strong>Click to explore the full dataset catalogue used for training</strong></summary>

 | **Supported Languages** | English, French, German, Italian, Japanese, Spanish, Chinese |
 | **Best For** | Agentic workflows, long-context reasoning, high-volume workloads (e.g. IT ticket automation), tool use, RAG |
 | **Reasoning Mode** | Configurable on/off via chat template (`enable_thinking=True/False`) |
 | **License** | [NVIDIA Nemotron Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/) |
 | **Release Date** | March 11, 2026 |
 ##### vLLM on DGX Spark
+To deploy the NVFP4 chekpoint on NVIDIA DGX Spark, make sure that you are using the `vllm/vllm-openai:v0.20.0` container image and use the following command:
 ```bash
 docker run --rm -it --gpus all \
   -v ~/.cache/huggingface:/root/.cache/huggingface \
   -v $(pwd)/super_v3_reasoning_parser.py:/app/super_v3_reasoning_parser.py \
   -p 8000:8000 \
+  vllm/vllm-openai:v0.20.0 \
     --model nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 \
     --served-model-name nvidia/nemotron-3-super \
     --host 0.0.0.0 \
     --moe-backend marlin \
     --mamba_ssm_cache_dtype float16 \
     --quantization fp4 \
+    --speculative_config '{"method":"mtp","num_speculative_tokens":3,"moe_backend":"triton"}' \
     --reasoning-parser-plugin /app/super_v3_reasoning_parser.py \
     --reasoning-parser super_v3 \
     --enable-auto-tool-choice \
 More details on the datasets and synthetic data generation methods can be found in the technical report _[**_NVIDIA Nemotron 3 Super_**](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Super-Technical-Report.pdf)_.
 <details>
 <summary><strong>Click to explore the full dataset catalogue used for training</strong></summary>