Instructions to use RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", trust_remote_code=True)
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 RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16

SGLang

How to use RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 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 "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16" \
    --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": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
		"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 "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16" \
        --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": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
```

robgreenberg3 commited on Apr 14

Commit

b4f6195

verified ·

1 Parent(s): 9a0b57e

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -281,7 +281,7 @@ export MODEL_CKPT=PATH/TO/MODEL/CHECKPOINT
 ```bash
 # Optional: --enable-expert-parallel
 vllm serve $MODEL_CKPT \
-  --served-model-name nvidia/nemotron-3-super \
   --async-scheduling \
   --dtype auto \
   --kv-cache-dtype fp8 \
@@ -316,7 +316,7 @@ For more detailed information, please see [this cookbook](https://github.com/NVI
 ```bash
 sglang serve \
   --model-path PATH/TO/CHECKPOINT \
-  --served-model-name nvidia/nemotron-3-super \
   --trust-remote-code \
   --tp 8 \
   --ep 8 \
@@ -379,7 +379,7 @@ The examples below use the OpenAI-compatible client and work with any of the ser
 ```python
 from openai import OpenAI
 client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
-MODEL = "nvidia/nemotron-3-super"
 ```
 **Reasoning ON (default)**
@@ -446,7 +446,7 @@ Create or update your `~/.config/opencode/opencode.json`:
             },
             "models": {
                 "nvidia-nemotron-3-super": {
-                    "name": "nvidia/nemotron-3-super",
                     "limit": {
                         "context": 1000000,
                         "output": 32768

 ```bash
 # Optional: --enable-expert-parallel
 vllm serve $MODEL_CKPT \
+  --served-model-name RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 \
   --async-scheduling \
   --dtype auto \
   --kv-cache-dtype fp8 \
 ```bash
 sglang serve \
   --model-path PATH/TO/CHECKPOINT \
+  --served-model-name RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 \
   --trust-remote-code \
   --tp 8 \
   --ep 8 \
 ```python
 from openai import OpenAI
 client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
+MODEL = "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"
 ```
 **Reasoning ON (default)**
             },
             "models": {
                 "nvidia-nemotron-3-super": {
+                    "name": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
                     "limit": {
                         "context": 1000000,
                         "output": 32768