Instructions to use nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4")
model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", 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-3.5-Lightning-30B-A3B-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-3.5-Lightning-30B-A3B-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-3.5-Lightning-30B-A3B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

SGLang

How to use nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-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-3.5-Lightning-30B-A3B-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-3.5-Lightning-30B-A3B-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-3.5-Lightning-30B-A3B-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-3.5-Lightning-30B-A3B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
```

Nvidia-NetanelHaber commited on 12 days ago

Commit

02fd987

verified ·

1 Parent(s): cc84af2

Explicitly set `VLLM_HUMMING_MOE_GEMM_TYPE=indexed` for humming, to prep for vllm main.

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -310,6 +310,7 @@ vllm serve --model $MODEL_CKPT \
 For max throughput deployments, use the following configuration, no speculative decoding strategy is best for this serving configuration, and due to memory constraints the Mamba cache `dtype` is set as FP16:
 ```shell
 vllm serve --model $MODEL_CKPT \
     --max-num-seqs 256 \
     --max-num-batched-tokens 16384 \
@@ -394,6 +395,7 @@ vllm serve --model $MODEL_CKPT \
 The same checkpoint also serves via W4A16 kernels, extending coverage to Ampere-class GPUs, like the A100 80GB:
 ```shell
 vllm serve --model nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 \
     --moe-backend humming \
     --linear-backend humming \

 For max throughput deployments, use the following configuration, no speculative decoding strategy is best for this serving configuration, and due to memory constraints the Mamba cache `dtype` is set as FP16:
 ```shell
+VLLM_HUMMING_MOE_GEMM_TYPE=indexed \
 vllm serve --model $MODEL_CKPT \
     --max-num-seqs 256 \
     --max-num-batched-tokens 16384 \
 The same checkpoint also serves via W4A16 kernels, extending coverage to Ampere-class GPUs, like the A100 80GB:
 ```shell
+VLLM_HUMMING_MOE_GEMM_TYPE=indexed \
 vllm serve --model nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 \
     --moe-backend humming \
     --linear-backend humming \