Instructions to use Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound with Transformers:

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

pipe = pipeline("text-generation", model="Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound")
model = AutoModelForCausalLM.from_pretrained("Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound", 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 Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound

SGLang

How to use Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound 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 "Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound" \
    --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": "Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound",
		"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 "Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound" \
        --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": "Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound with Docker Model Runner:
```
docker model run hf.co/Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound
```

Improve model card: Add pipeline tag, library name, and update paper/citation

by nielsr HF Staff - opened Dec 5, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+19

-8

Files changed (1) hide show

README.md +19 -8

README.md CHANGED Viewed

@@ -1,12 +1,15 @@
 ---
-license: mit
-datasets:
-- NeelNanda/pile-10k
 base_model:
 - deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
 ---
 ## Model Details
@@ -257,7 +260,7 @@ auto-round --eval  --model "Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound-inc"
 Here is the sample command to reproduce the model
 ```bash
-auto-round
 --model_name deepseek-ai/DeepSeek-R1-0528-Qwen3-8B \
 --device 0 \
 --format "auto_gptq,auto_awq,auto_round" \
@@ -287,6 +290,14 @@ The license on this model does not constitute legal advice. We are not responsib
 ## Cite
-@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
-[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)

 ---
 base_model:
 - deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
+datasets:
+- NeelNanda/pile-10k
+license: mit
+pipeline_tag: text-generation
+library_name: transformers
 ---
+This model is `Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound`, a quantized LLM based on the work presented in [SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs](https://huggingface.co/papers/2512.04746).
+The quantization was performed using the [AutoRound](https://github.com/intel/auto-round) algorithm.
 ## Model Details
 Here is the sample command to reproduce the model
 ```bash
+auto-round \
 --model_name deepseek-ai/DeepSeek-R1-0528-Qwen3-8B \
 --device 0 \
 --format "auto_gptq,auto_awq,auto_round" \
 ## Cite
+```bibtex
+@article{cheng2025signroundv2,
+      title={SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs},
+      author={Cheng, Wenhua and Zhang, Weiwei and Guo, Heng and Shen, Haihao},
+      year={2025},
+      eprint={2512.04746},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2512.04746},
+}
+```