Instructions to use deepseek-ai/DeepSeek-V3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V3.2 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V3.2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V3.2")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V3.2", device_map="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-V3.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V3.2"
# 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-V3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V3.2

SGLang

How to use deepseek-ai/DeepSeek-V3.2 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-V3.2" \
    --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-V3.2",
		"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-V3.2" \
        --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-V3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V3.2 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V3.2
```

May we please get a light-weight Deepseek model?

#27

by deleted - opened Dec 7, 2025

Discussion

deleted

Dec 7, 2025

My 16GB GPU and 64GB RAM cannot load something like this. I'd love to see a model within the 16b-32b range in the future, if that is possible. Thanks in advance.

owenqwenllmwine

Dec 8, 2025

For real, would be great to see smaller models from them and not these huge TB models that require a data center to run at any usable speed much less load.

kth8

Dec 9, 2025

I think Deepseek is more interested in trying to push the frontier rather than catering to edge devices.

owenqwenllmwine

Dec 9, 2025

I think Deepseek is more interested in trying to push the frontier rather than catering to edge devices.

Fair but it would be nice to have a light weight deepseek model that CAN run on smaller devices.

YYYAMS

Dec 30, 2025

I'm testing a distributed cluster to run this full-weights on consumer cards (pooling 4090s) to bypass the VRAM limit. let me know if you want to run a test job.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment