Instructions to use Huang2020/Qwen3-4B-Domino-b16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Huang2020/Qwen3-4B-Domino-b16 with Transformers:

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

pipe = pipeline("text-generation", model="Huang2020/Qwen3-4B-Domino-b16", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("Huang2020/Qwen3-4B-Domino-b16", trust_remote_code=True)
model = AutoModel.from_pretrained("Huang2020/Qwen3-4B-Domino-b16", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Huang2020/Qwen3-4B-Domino-b16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Huang2020/Qwen3-4B-Domino-b16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Huang2020/Qwen3-4B-Domino-b16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Huang2020/Qwen3-4B-Domino-b16

SGLang

How to use Huang2020/Qwen3-4B-Domino-b16 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 "Huang2020/Qwen3-4B-Domino-b16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Huang2020/Qwen3-4B-Domino-b16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Huang2020/Qwen3-4B-Domino-b16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Huang2020/Qwen3-4B-Domino-b16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Huang2020/Qwen3-4B-Domino-b16 with Docker Model Runner:
```
docker model run hf.co/Huang2020/Qwen3-4B-Domino-b16
```

Qwen3-4B Domino Draft Model

Paper | GitHub

This repository contains a Domino/DFlash draft model for speculative decoding with Qwen/Qwen3-4B. The draft model is not intended to be used as a standalone language model; it should be paired with the target model during generation.

Domino keeps draft generation block-parallel while adding a lightweight causal correction head. This preserves the low drafting cost of parallel speculative decoding and improves draft-token acceptance.

Model Details

Target model: Qwen/Qwen3-4B
Draft model: Huang2020/Qwen3-4B-Domino-b16
Block size: 16
Recommended usage: one GPU for the direct spec_generate path
Qwen3 chat setting: thinking mode disabled

Installation

uv pip install "git+https://github.com/jianuo-huang/sglang.git@feat/domino-tensor-parallel#subdirectory=python"

Quick Usage

SGLang

sglang serve \
  --model-path Qwen/Qwen3-4B \
  --speculative-algorithm DFLASH \
  --speculative-draft-model-path Huang2020/Qwen3-4B-Domino-b16

Transformers

from transformers import AutoModel, AutoModelForCausalLM, AutoTokenizer

draft = AutoModel.from_pretrained(
    "Huang2020/Qwen3-4B-Domino-b16",
    trust_remote_code=True,
    torch_dtype="auto",
    device_map="cuda:0",
).eval()

target = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3-4B",
    torch_dtype="auto",
    device_map="cuda:0",
).eval()

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B")
messages = [{
    "role": "user",
    "content": "How many positive whole-number divisors does 196 have?",
}]
input_ids = tokenizer.apply_chat_template(
    messages,
    return_tensors="pt",
    return_dict=False,
    add_generation_prompt=True,
    enable_thinking=False,
).to(draft.device)

output = draft.spec_generate(
    input_ids=input_ids,
    target=target,
    max_new_tokens=2048,
    temperature=0.0,
    stop_token_ids=[tokenizer.eos_token_id],
)

generated = output[:, input_ids.shape[1]:]
print(tokenizer.decode(generated[0], skip_special_tokens=True))

Benchmark Figure

The source PDF is available at assets/speedup.pdf.

Citation

@article{huang2026domino,
  title={Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding},
  author={Huang, Jianuo and Zhang, Yaojie and Zhang, Qituan and Lin, Hao and Xu, Hanlin and Zhang, Linfeng},
  journal={arXiv preprint arXiv:2605.29707},
  year={2026}
}