Instructions to use bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/DeepSeek-R1-Distill-Qwen-14B-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-14B-GGUF",
	filename="DeepSeek-R1-Distill-Qwen-14B-IQ2_M.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 bartowski/DeepSeek-R1-Distill-Qwen-14B-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 bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/DeepSeek-R1-Distill-Qwen-14B-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-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/DeepSeek-R1-Distill-Qwen-14B-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-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/DeepSeek-R1-Distill-Qwen-14B-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-14B-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-14B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M

Ollama
How to use bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF with Ollama:
```
ollama run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M
```

Unsloth Studio

How to use bartowski/DeepSeek-R1-Distill-Qwen-14B-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-14B-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-14B-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-14B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-R1-Distill-Qwen-14B-GGUF-Q4_K_M

List all available models

lemonade list

Not impressed?

by urtuuuu - opened Jan 20, 2025

Discussion

urtuuuu

Jan 20, 2025

•

edited Jan 20, 2025

I'm not sure, maybe it doesn't like my usual test questions, but it performs worse than phi-4 it seems. For example this pretty easy question >>>
There are three killers in a room. Someone enters the room and kills one of them. Nobody leaves the room. How many killers are left in the room?

think
Alright, let's break this down step by step to understand the problem clearly.
First, there are initially three killers in the room. Then, someone enters the room and kills one of them. After that, it's mentioned that nobody leaves the room.
So, initially, there are three killers. When someone enters, they kill one killer. This means that one killer is removed from the group. Since nobody leaves after the killing occurs, we only need to account for the remaining individuals in the room.
Therefore, by subtracting the one killed from the initial number of killers, we can determine how many killers remain.
/think

After the person enters and kills one killer, there are two killers left in the room.

llama.cpp build: 4518, build-in template. temp 0.5-0.7, rep pen 1.1

deleted

Jan 25, 2025

•

edited Jan 25, 2025

For me the model is pretty terrible too, NeMo is still far greater in coherence and following instructions. I think it has to do with this model's terrible instruct format, I dunno... well, I hope so. It's a promising model on paper, I'd prefer to see it perform... Maybe a ChatML version would be better.

jattoedaltni

Jan 31, 2025

Maybe the fact that it was designed in a different language has something to do with it... IDK. I can easily prompt my current best LLMs to create a plan before going about something, and it does just fine with that.

BobaScript

Feb 15, 2025

•

edited Feb 15, 2025

The answer to the question would not be two, though- but three. If there are three killers in the room, let's represent them with the letter X:

X X X

One person enters the room, we will represent them with the letter O.

X X X O

Now that person Kills one of the three killers.

X X O

That person is now also a killer. So O now becomes X. As soon as O killed an X, he is no longer able to be a O. His status has changed.

Thus, if no one left the room- there are still 3 killers in the room at the end of the equation.

X X X

The question would only work if you asked how many original killers remained in the room; then it would be 2.

beywvbgwnsnbc

Feb 15, 2025

Really, the answer is 4, since the question does not mention dead or alive.

So there are 4 killers in the room, 3 alive (supposed alive) and 1 dead.

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