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

Libraries

How to use deepseek-ai/DeepSeek-V4-Flash-Vision-Exp with Transformers:

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

pipe = pipeline("image-text-to-text", model="deepseek-ai/DeepSeek-V4-Flash-Vision-Exp")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-V4-Flash-Vision-Exp 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-Flash-Vision-Exp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

SGLang

How to use deepseek-ai/DeepSeek-V4-Flash-Vision-Exp 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-Flash-Vision-Exp" \
    --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": "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
		"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 "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp" \
        --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": "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

It's better to have a lite version a 120b a10b

by linghuchong1995 - opened about 12 hours ago

Discussion

linghuchong1995

about 12 hours ago

Perfectly suited for 128GB of unified memory.

TRex-face

about 12 hours ago

Hard pass, the current version is already suffering because it is quantised 4 bit and no 8 bit for it exists. Could have worked so much better if they released the full FP8 version for it.

Banaxi-Tech

about 12 hours ago

YES FOR 96G MACs too

nraxl1

about 8 hours ago

its fp4 QAT afaik

freda2

about 7 hours ago

Hard pass, the current version is already suffering because it is quantised 4 bit and no 8 bit for it exists. Could have worked so much better if they released the full FP8 version for it.

I would challenge you to provide an alternative that beats DS4F at this relatively small actual loaded weight size with similar speed, accuracy and memory usage including kv cache.

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