Instructions to use UT-IFML/dQwen3.5-9B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UT-IFML/dQwen3.5-9B-Base with Transformers:

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

pipe = pipeline("text-generation", model="UT-IFML/dQwen3.5-9B-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("UT-IFML/dQwen3.5-9B-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use UT-IFML/dQwen3.5-9B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UT-IFML/dQwen3.5-9B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UT-IFML/dQwen3.5-9B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/UT-IFML/dQwen3.5-9B-Base

SGLang

How to use UT-IFML/dQwen3.5-9B-Base 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 "UT-IFML/dQwen3.5-9B-Base" \
    --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": "UT-IFML/dQwen3.5-9B-Base",
		"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 "UT-IFML/dQwen3.5-9B-Base" \
        --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": "UT-IFML/dQwen3.5-9B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use UT-IFML/dQwen3.5-9B-Base with Docker Model Runner:
```
docker model run hf.co/UT-IFML/dQwen3.5-9B-Base
```

dQwen3.5-9B-Base

A masked diffusion language model adapted from Qwen3.5-9B. The backbone is hybrid: only its attention layers are made bidirectional, and the Gated DeltaNet layers stay causal. This is a base model, with no instruction tuning.

Paper: dQwen3.5: Hybrid-Attention Diffusion Language Models. Code: https://github.com/AntonXue/dQwen

The dQwen3.5 family

model	total params	backbone
dQwen3.5-0.8B-Base	0.75B	hybrid
dQwen3.5-2B-Base	1.88B	hybrid
dQwen3.5-4B-Base	4.21B	hybrid
dQwen3.5-9B-Base (this repo)	8.95B	hybrid
dQwen3-1.7B-Base	1.72B	full attention (control)

Quickstart

Needs a CUDA GPU and transformers>=5.13 (tested with torch 2.7.1+cu128, flash-linear-attention 0.5.1).

import torch
from transformers import AutoModel

model = AutoModel.from_pretrained("UT-IFML/dQwen3.5-9B-Base", trust_remote_code=True, dtype=torch.bfloat16).cuda().eval()
print(model.generate("def fibonacci(n):", gen_length=512, stop_strings=["\ndef "]).text)

generate decodes the whole canvas at once, committing positions above a confidence threshold (tau=0.9); pass block_length=32 for left-to-right block decoding, or tau=None, steps_per_block=k for a fixed budget. The 50B-token checkpoint from the paper is revision="step25000-swa".

Citation

@article{xue2026dqwen,
  title   = {dQwen3.5: Hybrid-Attention Diffusion Language Models},
  author  = {Xue, Anton and Rout, Litu and Akella, Aditya and Klivans, Adam and Sanghavi, Sujay and Shakkottai, Sanjay},
  journal = {arXiv preprint arXiv:2609.20751},
  year    = {2026}
}