Instructions to use unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF")
model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF: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-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF: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-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/DeepSeek-R1-0528-Qwen3-8B-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-R1-0528-Qwen3-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/DeepSeek-R1-0528-Qwen3-8B-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-R1-0528-Qwen3-8B-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-R1-0528-Qwen3-8B-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-R1-0528-Qwen3-8B-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-R1-0528-Qwen3-8B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF with Ollama:
```
ollama run hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL
```
Unsloth Desktop

How to use unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.DeepSeek-R1-0528-Qwen3-8B-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:UD-Q4_K_XL" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

How to disable reasoning?

by SlavikF - opened May 30, 2025

Discussion

SlavikF

May 30, 2025

•

edited May 30, 2025

I'm using this model with llama.cpp + openWebUI.

Is it possible to disable reasoning for this model?

I tried "/nothink" tag in the prompt - doesn't do anything.

I wonder, if I need to use special prompt? Or any other solution?

shimmyshimmer

Unsloth AI org May 30, 2025

I don't think you can because they fine-tuned the base version of the model

VastishSlurry

May 30, 2025

If your front end supports something similar to SillyTavern's "Start Reply With" feature, you can pre-fill your own thinking block and the response will proceed straight to the answer. Here's the pre-fill I use for that:

<think>
Okay.
</think>

MrDevolver

May 30, 2025

If your front end supports something similar to SillyTavern's "Start Reply With" feature, you can pre-fill your own thinking block and the response will proceed straight to the answer. Here's the pre-fill I use for that:
<think>
Okay.
</think>

You don't even need to put anything into think tags like "Okay" in your example. Just empty think tags will do. On the other hand though, while this method works fairly well, in practice it means filling your context window with garbage tokens that will be never really useful for anything context-wise. In one-shot scenarios where you just want a straight answer from the AI to a single question, this is a good solution. However, in roleplay scenarios where you need to have back and forth conversation with the AI, adding these extra tokens (think tags) just to prevent the AI from thinking before answering is less than ideal. It'd be best to finetune the model on roleplay data that would override this thinking habbit to prevent filling the context window with garbage tokens.

owao

Jul 14, 2025

@SlavikF I don't currently have this model in my library, but did you try /no_thinkinstead? Because I had the issue with Qwen3 models mistyping it! Maybe they use the same special token would need to check their ...

Edit lol: looking at https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/raw/main/tokenizer.json, the dictionary unfortunately doesn't contain such /think, /nothink(neither /no_think), it's all or nothing :D
So only solution is already mentioned (I think it's called hot steering or test time steering). But Openwebui doesn't allow editing the thoughts, even afterward (that's sad cause this kind of steering can be useful for when you see a mistake in the reasoning and want to force it take another path, sort of taking advantage of the "token level continuous checkpointing").

AtAndDev

Jul 14, 2025

You can write something like "Okay, I think I am ready to answer." to bypass thinking. Plus some research concluded that the reasoning process isnt that important an the rl is just amplifying the "good" answers likelihood.

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