DeepSeek-R1-Distill-Qwen-14B

Instructions to use VECTORVV1/DeepSeek-R1-Distill-Qwen-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VECTORVV1/DeepSeek-R1-Distill-Qwen-14B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="VECTORVV1/DeepSeek-R1-Distill-Qwen-14B",
	filename="DeepSeek-R1-Distill-Qwen-14B-MXFP4-Aggressive.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use VECTORVV1/DeepSeek-R1-Distill-Qwen-14B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf VECTORVV1/DeepSeek-R1-Distill-Qwen-14B
# Run inference directly in the terminal:
llama-cli -hf VECTORVV1/DeepSeek-R1-Distill-Qwen-14B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf VECTORVV1/DeepSeek-R1-Distill-Qwen-14B
# Run inference directly in the terminal:
llama-cli -hf VECTORVV1/DeepSeek-R1-Distill-Qwen-14B

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 VECTORVV1/DeepSeek-R1-Distill-Qwen-14B
# Run inference directly in the terminal:
./llama-cli -hf VECTORVV1/DeepSeek-R1-Distill-Qwen-14B

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 VECTORVV1/DeepSeek-R1-Distill-Qwen-14B
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VECTORVV1/DeepSeek-R1-Distill-Qwen-14B

Use Docker

docker model run hf.co/VECTORVV1/DeepSeek-R1-Distill-Qwen-14B

LM Studio
Jan
Ollama
How to use VECTORVV1/DeepSeek-R1-Distill-Qwen-14B with Ollama:
```
ollama run hf.co/VECTORVV1/DeepSeek-R1-Distill-Qwen-14B
```

Unsloth Studio new

How to use VECTORVV1/DeepSeek-R1-Distill-Qwen-14B 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 VECTORVV1/DeepSeek-R1-Distill-Qwen-14B 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 VECTORVV1/DeepSeek-R1-Distill-Qwen-14B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for VECTORVV1/DeepSeek-R1-Distill-Qwen-14B to start chatting

Pi new

How to use VECTORVV1/DeepSeek-R1-Distill-Qwen-14B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf VECTORVV1/DeepSeek-R1-Distill-Qwen-14B

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DeepSeek-R1-Distill-Qwen-14B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use VECTORVV1/DeepSeek-R1-Distill-Qwen-14B with Docker Model Runner:
```
docker model run hf.co/VECTORVV1/DeepSeek-R1-Distill-Qwen-14B
```

Lemonade

How to use VECTORVV1/DeepSeek-R1-Distill-Qwen-14B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VECTORVV1/DeepSeek-R1-Distill-Qwen-14B

Run and chat with the model

lemonade run user.DeepSeek-R1-Distill-Qwen-14B-{{QUANT_TAG}}

List all available models

lemonade list

GPT-OSS-20B-Uncensored-HauhauCS-Aggressive

Join the Discord for updates, roadmaps, projects, or just to chat.

Uncensored version of GPT-OSS 20B. This is the aggressive variant - tuned harder for fewer refusals.

If you want something more conservative, check out the Balanced variant.

Format

MXFP4 GGUF. Works with llama.cpp, ollama, LM Studio, and anything else that loads GGUFs.

LM Studio

Compatible with Reasoning Effort custom buttons. To use them, put the model in:

LM Models\lmstudio-community\gpt-oss-20b-GGUF\

About

Base model: GPT-OSS 20B
Abliterated with custom tooling
Pick this one if you want maximum uncensoring

Downloads last month: 345

GGUF

Model size

21B params

Architecture

gpt-oss

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support