Instructions to use bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF",
	filename="DeepSeek-R1-Distill-Qwen-32B-IQ2_M.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 bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-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 bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-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 bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-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 bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/DeepSeek-R1-Distill-Qwen-32B-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": "bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M

Ollama
How to use bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF with Ollama:
```
ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M
```

Unsloth Studio

How to use bartowski/DeepSeek-R1-Distill-Qwen-32B-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 bartowski/DeepSeek-R1-Distill-Qwen-32B-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 bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF to start chatting

Docker Model Runner
How to use bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-R1-Distill-Qwen-32B-GGUF-Q4_K_M

List all available models

lemonade list

Oobabooga Errors

by SekkSea - opened Jan 20, 2025

Discussion

SekkSea

Jan 20, 2025

I just tried to load Q5_K_M in Oobabooga. I updated Oobabooga a few minute ago. It's still not having it. Every other model works, so I'm guessing this one is going to be like Nemotron 51b, with Oobabooga users having to wait for an update.

ERROR DUMP:
llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'deepseek-r1-qwen'
llama_model_load_from_file: failed to load model
17:14:52-135613 ERROR Failed to load the model.
Traceback (most recent call last):
File "C:\AI\text-generation-webui-main\modules\ui_model_menu.py", line 214, in load_model_wrapper
shared.model, shared.tokenizer = load_model(selected_model, loader)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\AI\text-generation-webui-main\modules\models.py", line 90, in load_model
output = load_func_maploader
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\AI\text-generation-webui-main\modules\models.py", line 280, in llamacpp_loader
model, tokenizer = LlamaCppModel.from_pretrained(model_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\AI\text-generation-webui-main\modules\llamacpp_model.py", line 111, in from_pretrained
result.model = Llama(**params)
^^^^^^^^^^^^^^^
File "C:\AI\text-generation-webui-main\installer_files\env\Lib\site-packages\llama_cpp_cuda_tensorcores\llama.py", line 369, in init
internals.LlamaModel(
File "C:\AI\text-generation-webui-main\installer_files\env\Lib\site-packages\llama_cpp_cuda_tensorcores_internals.py", line 56, in init
raise ValueError(f"Failed to load model from file: {path_model}")
ValueError: Failed to load model from file: models\Deepseek-R1-Qwen-32b-Q5_K_M_GGUF\DeepSeek-R1-Distill-Qwen-32B-Q5_K_M.gguf

Exception ignored in: <function LlamaCppModel.__del__ at 0x000002363D489120>
Traceback (most recent call last):
File "C:\AI\text-generation-webui-main\modules\llamacpp_model.py", line 62, in del
del self.model
^^^^^^^^^^
AttributeError: 'LlamaCppModel' object has no attribute 'model'

Nindaleth

Jan 21, 2025

unknown pre-tokenizer type: 'deepseek-r1-qwen'

I'm guessing this one is going to be like Nemotron 51b, with Oobabooga users having to wait for an update

Yes, that's right.

charltonh

Jan 23, 2025

Same: llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'deepseek-r1-qwen'

SekkSea

Jan 23, 2025

As per the instructions, I just downloaded LM Studio. and It works there. It's a small download, and easy to use.

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