Instructions to use unsloth/DeepSeek-R1-GGUF-UD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/DeepSeek-R1-GGUF-UD with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/DeepSeek-R1-GGUF-UD", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/DeepSeek-R1-GGUF-UD", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-R1-GGUF-UD", trust_remote_code=True)

llama-cpp-python

How to use unsloth/DeepSeek-R1-GGUF-UD with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/DeepSeek-R1-GGUF-UD",
	filename="BF16/DeepSeek-R1-BF16-00001-of-00030.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/DeepSeek-R1-GGUF-UD with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/DeepSeek-R1-GGUF-UD with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

SGLang

How to use unsloth/DeepSeek-R1-GGUF-UD 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 "unsloth/DeepSeek-R1-GGUF-UD" \
    --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": "unsloth/DeepSeek-R1-GGUF-UD",
		"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 "unsloth/DeepSeek-R1-GGUF-UD" \
        --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": "unsloth/DeepSeek-R1-GGUF-UD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/DeepSeek-R1-GGUF-UD with Ollama:
```
ollama run hf.co/unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/DeepSeek-R1-GGUF-UD with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/DeepSeek-R1-GGUF-UD to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/DeepSeek-R1-GGUF-UD to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/DeepSeek-R1-GGUF-UD to start chatting

Docker Model Runner
How to use unsloth/DeepSeek-R1-GGUF-UD with Docker Model Runner:
```
docker model run hf.co/unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL
```

Lemonade

How to use unsloth/DeepSeek-R1-GGUF-UD with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/DeepSeek-R1-GGUF-UD:UD-Q4_K_XL

Run and chat with the model

lemonade run user.DeepSeek-R1-GGUF-UD-UD-Q4_K_XL

List all available models

lemonade list

danielhanchen commited on Apr 23, 2025

Commit

17c12b7

verified ·

1 Parent(s): 14e4c44

Add files using upload-large-folder tool

Browse files

Files changed (16) hide show

.gitattributes +15 -0
Q8_0/DeepSeek-R1-Q8_0-00001-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00002-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00003-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00004-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00005-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00006-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00007-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00008-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00009-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00010-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00011-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00012-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00013-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00014-of-00015.gguf +3 -0
Q8_0/DeepSeek-R1-Q8_0-00015-of-00015.gguf +3 -0

@@ -136,3 +136,18 @@ Q3_K_M/DeepSeek-R1-Q3_K_M-00001-of-00007.gguf filter=lfs diff=lfs merge=lfs -tex
 Q2_K_L/DeepSeek-R1-Q2_K_L-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
 Q2_K_L/DeepSeek-R1-Q2_K_L-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
 Q3_K_M/DeepSeek-R1-Q3_K_M-00005-of-00007.gguf filter=lfs diff=lfs merge=lfs -text

 Q2_K_L/DeepSeek-R1-Q2_K_L-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
 Q2_K_L/DeepSeek-R1-Q2_K_L-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
 Q3_K_M/DeepSeek-R1-Q3_K_M-00005-of-00007.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00015-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00003-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00008-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00004-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00014-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00013-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00001-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00010-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00011-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00012-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00009-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00002-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00007-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00005-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/DeepSeek-R1-Q8_0-00006-of-00015.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3fc12d849ea5edd003e8f8c773d3eaac6bbbb6928098fa8ac7ed2e9b41e7ad
+size 47784555968

+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf18d71ff8e4639899930423ab82059eadb34667604754e476aaef6b2627ecc
+size 48927728256

+version https://git-lfs.github.com/spec/v1
+oid sha256:0a7d8a3d20538f672effe342051dd0adad93496d37f58ef1c707156aeca58fd2
+size 48927728320

+version https://git-lfs.github.com/spec/v1
+oid sha256:b61e86c88453ec0d2a361b8e8c363dcbacc49ab49389e8e857dc31cf38d9e06e
+size 29441495680

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@