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
```

Chris-Alexiuk

SaylorTwift HF Staff commited on 4 days ago

Commit

e8f3c7c

1 Parent(s): 3dbda56

Add community evaluation results (#8)

Browse files

- Add community evaluation results (778647c930624440f0b6df40de651180f95c1994)

Co-authored-by: Nathan Habib <SaylorTwift@users.noreply.huggingface.co>

Files changed (1) hide show

.eval_results/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4.yaml +45 -0

.eval_results/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4.yaml ADDED Viewed

	@@ -0,0 +1,45 @@

+- dataset:
+    id: TIGER-Lab/MMLU-Pro
+    task_id: mmlu_pro
+  value: 81.62
+  date: "2026-08-13"
+  source:
+    url: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
+    name: "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 model card"
+- dataset:
+    id: Idavidrein/gpqa
+    task_id: diamond
+  value: 75.57
+  date: "2026-08-13"
+  source:
+    url: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
+    name: "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 model card"
+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 10.47
+  date: "2026-08-13"
+  source:
+    url: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
+    name: "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 model card"
+  notes: "Text-only, no tools — HLE's default includes image questions, so this excludes the multimodal subset."
+- dataset:
+    id: SWE-bench/SWE-bench_Verified
+    task_id: swe_bench_%_resolved
+  value: 52.80
+  date: "2026-08-13"
+  source:
+    url: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
+    name: "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 model card"
+- dataset:
+    id: SWE-bench/SWE-bench_Multilingual
+    task_id: swe_bench_multilingual_%_resolved
+  value: 36.47
+  date: "2026-08-13"
+  source:
+    url: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
+    name: "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 model card"