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

Libraries

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

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

pipe = pipeline("text-generation", model="unsloth/DeepSeek-R1-GGUF", 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", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-R1-GGUF", trust_remote_code=True)

llama-cpp-python

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/DeepSeek-R1-GGUF",
	filename="DeepSeek-R1-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

llama.cpp

How to use unsloth/DeepSeek-R1-GGUF 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:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf unsloth/DeepSeek-R1-GGUF:Q4_K_M

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:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf unsloth/DeepSeek-R1-GGUF:Q4_K_M

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:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf unsloth/DeepSeek-R1-GGUF:Q4_K_M

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:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/DeepSeek-R1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

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

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1-GGUF:Q4_K_M

SGLang

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

Ollama
How to use unsloth/DeepSeek-R1-GGUF with Ollama:
```
ollama run hf.co/unsloth/DeepSeek-R1-GGUF:Q4_K_M
```

Unsloth Studio new

How to use unsloth/DeepSeek-R1-GGUF 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 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 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 to start chatting

Docker Model Runner
How to use unsloth/DeepSeek-R1-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/DeepSeek-R1-GGUF:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/DeepSeek-R1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-R1-GGUF-Q4_K_M

List all available models

lemonade list

any benchmark results?

#22

by lxww301 - opened Feb 7, 2025

Discussion

lxww301

Feb 7, 2025

Thx for sharing the model, although it has impressive generation speed and flappybird results, it would be much better if there are any benchmark results

shimmyshimmer

Unsloth AI org Feb 8, 2025

•

edited Feb 25, 2025

Thx for sharing the model, although it has impressive generation speed and flappybird results, it would be much better if there are any benchmark results

See here for benchmarks on the test results: https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device/deepseek-r1-dynamic-1.58-bit

See an example of our Dynamic Quant's performance on the Hugging Face OpenLLM Leaderboard specifically for Phi-4: https://unsloth.ai/blog/dynamic-4bit

kotyKD

Feb 8, 2025

See here for benchmarks on the test results: https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device/deepseek-r1-dynamic-1.58-bit

Those are not benchmark results, that's just a more scientific way of measuring performance on 1 prompt. We want actual benchmarks. Tokens per second speed measured on different hardware would also be nice. By the way, asking a model to make a game that has an endless number of clones on GitHub does not really measure performance, it mainly measures how well the model can recite memorized code, it's not performance, it's just testing memory. I don't mean to be rude, but please don't act like this is sufficient as a benchmark. It just isn't. Please provide actual benchmark results at least, and if possible, also the tokens per second speed on different hardware. And if you do the tokens per second measurements, make sure you say how fast it is for a single user, not just the overall throughput performance. Thanks.

ngoquanghuy

Feb 25, 2025

See here for benchmarks on the test results: https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device/deepseek-r1-dynamic-1.58-bit

Those are not benchmark results, that's just a more scientific way of measuring performance on 1 prompt. We want actual benchmarks. Tokens per second speed measured on different hardware would also be nice. By the way, asking a model to make a game that has an endless number of clones on GitHub does not really measure performance, it mainly measures how well the model can recite memorized code, it's not performance, it's just testing memory. I don't mean to be rude, but please don't act like this is sufficient as a benchmark. It just isn't. Please provide actual benchmark results at least, and if possible, also the tokens per second speed on different hardware. And if you do the tokens per second measurements, make sure you say how fast it is for a single user, not just the overall throughput performance. Thanks.

Well said!

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