Instructions to use nvidia/Efficient-DLM-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Efficient-DLM-4B with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Efficient-DLM-4B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("nvidia/Efficient-DLM-4B", trust_remote_code=True)
model = AutoModel.from_pretrained("nvidia/Efficient-DLM-4B", 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

vLLM

How to use nvidia/Efficient-DLM-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Efficient-DLM-4B"
# 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/Efficient-DLM-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Efficient-DLM-4B

SGLang

How to use nvidia/Efficient-DLM-4B 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/Efficient-DLM-4B" \
    --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/Efficient-DLM-4B",
		"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/Efficient-DLM-4B" \
        --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/Efficient-DLM-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Efficient-DLM-4B with Docker Model Runner:
```
docker model run hf.co/nvidia/Efficient-DLM-4B
```

Efficient-DLM-4B / README.md

YongganFu

Initial release of Efficient-DLM-4B

d28c316 5 days ago

preview code

raw

history blame contribute delete

2.41 kB

	---
	library_name: transformers
	license: other
	license_name: cc-by-nc-4.0
	pipeline_tag: text-generation
	---

	# Efficient-DLM-4B

	<p align="center">
	📄 <a href="https://arxiv.org/pdf/2512.14067">Tech Report</a> &nbsp&nbsp\|&nbsp&nbsp 🤗 <a href="https://huggingface.co/nvidia/Efficient-DLM-4B">Efficient-DLM-4B</a> &nbsp&nbsp\|&nbsp&nbsp 🤗 <a href="https://huggingface.co/nvidia/Efficient-DLM-8B">Efficient-DLM-8B</a>
	</p>


	## Model Overview

	Efficient-DLM-4B is a base diffusion language model designed for parallel generation. It converts pretrained AR LMs into diffusion LMs through efficient continuous pretraining, enabling faster decoding while preserving the task accuracy of strong AR models. Efficient-DLM features block-wise attention with clean-context conditioning for KV-cache-friendly decoding, as well as position-dependent token masking to reduce the training–test mismatch in diffusion generation. See our [paper](https://arxiv.org/abs/2512.14067) for more technical details.

	<div align="center">
	<img src="https://huggingface.co/nvidia/Efficient-DLM-4B/resolve/main/images/result.png" alt="Accuracy vs throughput Pareto curve" width="500">
	</div>


	## Environment

	```bash
	transformers>=4.52.2
	```


	## Chat with Efficient-DLM-4B

	```python
	from transformers import AutoModel, AutoTokenizer
	import torch

	repo_name = "nvidia/Efficient-DLM-4B"

	tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
	model = AutoModel.from_pretrained(repo_name, trust_remote_code=True)
	model = model.cuda().to(torch.bfloat16)

	user_input = input("User: ").strip()

	prompt_ids = tokenizer(user_input, return_tensors="pt").input_ids.to(device="cuda")
	out_ids, nfe = model.generate(
	prompt_ids,
	max_new_tokens=128,
	steps=128,
	block_length=32,
	shift_logits=False,
	temperature=0.7,
	threshold=0.9,
	)

	response = tokenizer.batch_decode(out_ids[:, prompt_ids.shape[1]:], skip_special_tokens=True)[0]
	print(f"Model: {response}")
	print(f"[Num Function Eval (NFE)={nfe}]")
	```


	## Citation

	```
	@article{fu2025efficient,
	title={Efficient-dlm: From autoregressive to diffusion language models, and beyond in speed},
	author={Fu, Yonggan and Whalen, Lexington and Ye, Zhifan and Dong, Xin and Diao, Shizhe and Liu, Jingyu and Wu, Chengyue and Zhang, Hao and Xie, Enze and Han, Song and others},
	journal={arXiv preprint arXiv:2512.14067},
	year={2025}
	}
	```