Instructions to use deepseek-ai/DeepSeek-V4.1-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V4.1-Flash with Transformers:

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

pipe = pipeline("image-text-to-text", model="deepseek-ai/DeepSeek-V4.1-Flash")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4.1-Flash", device_map="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-V4.1-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V4.1-Flash"
# 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-V4.1-Flash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V4.1-Flash

SGLang

How to use deepseek-ai/DeepSeek-V4.1-Flash 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-V4.1-Flash" \
    --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-V4.1-Flash",
		"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-V4.1-Flash" \
        --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-V4.1-Flash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V4.1-Flash with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V4.1-Flash
```

OpenAI and Claude don't make me download half a terabyte of weight just to ask a question smh

#18

by Mikkkkoooo - opened 1 day ago

Discussion

Mikkkkoooo

1 day ago

I DONT GAF ABOUT THE WEIGHTS AND SAFETENSORS! I just wan to download the damn .exe and run it make no mistake.

WHY IS THERE CODE AND WTH IS THE SAFETENZORS??? WE HAVE GPT AND CLAU JUST GIVE US A CHAT BOX. It seems like these platforms think everyone has an 8x H200 cluster running in their bedroom and understands how to shard 500B parameters. well i am not and i dont understand it!

Regular users are not machine learning engineers and do not understand it. People only know how to type into a prompt and hit enter. SO WHY IS THERE RAW CODE? Make a website or sth and let people use it. Absolute nonsense.

jimmyL-llm

1 day ago

•

edited 1 day ago

Yeah, bro, there is. Just put your API into CC Switch, and your Claude code will be successfully possessed.

SudoUser

1 day ago

https://chat.deepseek.com/ use google bro

YannickGaspar

1 day ago

https://github.com/twitter/the-algorithm/issues/1999

No one here got the reference lol

spacexujing

1 day ago

•

edited 1 day ago

Bro walk into a beer bar and compling about they only sell beer and get angry about they don't sell cups. Even the owner do have a cup stop next door.

Edit: Well, deepseek fails to figure out this is a meme. Seems still not good enough(

AsThirtyThree

1 day ago

I DONT GAF ABOUT THE WEIGHTS AND SAFETENSORS! I just wan to download the damn .exe and run it make no mistake.

WHY IS THERE CODE AND WTH IS THE SAFETENZORS??? WE HAVE GPT AND CLAU JUST GIVE US A CHAT BOX. It seems like these platforms think everyone has an 8x H200 cluster running in their bedroom and understands how to shard 500B parameters. well i am not and i dont understand it!

Regular users are not machine learning engineers and do not understand it. People only know how to type into a prompt and hit enter. SO WHY IS THERE RAW CODE? Make a website or sth and let people use it. Absolute nonsense.

use gguf instead.

CreitinGameplays

1 day ago

i got the joke

enpi-bald

1 day ago

I think they're actually happy to download such big files

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