Instructions to use deepseek-ai/DeepSeek-V4-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V4-Pro with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V4-Pro")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Pro")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Pro", device_map="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-V4-Pro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V4-Pro"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V4-Pro

SGLang

How to use deepseek-ai/DeepSeek-V4-Pro 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 "deepseek-ai/DeepSeek-V4-Pro" \
    --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": "deepseek-ai/DeepSeek-V4-Pro",
		"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 "deepseek-ai/DeepSeek-V4-Pro" \
        --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": "deepseek-ai/DeepSeek-V4-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V4-Pro with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V4-Pro
```

知识截止时效性建议：模型需更紧密跟进开源生态动态

#185

by xbb19730559 - opened May 20

Discussion

xbb19730559

May 20

作为一个日常重度使用 DeepSeek API（Pro 模型）的开发者，想提一个务实的建议：

今天用 Pro 模型在 Mac Studio (256GB) 上部署 DeepSeek V4 Flash 本地推理，全过程暴露了模型知识截止后的严重断层：

不知道 antirez (Redis 创始人) 在 HuggingFace 上发布了专门针对 Mac 的 GGUF 量化版（antirez/deepseek-v4-gguf，IQ2XXS 80GB），已获 26 万+ 下载
不知道他的 llama.cpp-deepseek-v4-flash 分支和 ds4 推理引擎已在 GitHub 开源
不知道 MLX 社区版（mlx-community）对 DSV4 的支持仍是实验阶段
建议用 ModelScope 国内源下载，但没验证该模型是否存在于 ModelScope 上

这些信息在 HuggingFace / GitHub / Discord 上是实时更新的，但模型完全不知道。

建议：