Instructions to use cortexso/deepseek-r1-distill-qwen-32b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cortexso/deepseek-r1-distill-qwen-32b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cortexso/deepseek-r1-distill-qwen-32b",
	filename="deepseek-r1-distill-qwen-32b-q2_k.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 cortexso/deepseek-r1-distill-qwen-32b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/deepseek-r1-distill-qwen-32b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/deepseek-r1-distill-qwen-32b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/deepseek-r1-distill-qwen-32b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/deepseek-r1-distill-qwen-32b: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 cortexso/deepseek-r1-distill-qwen-32b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cortexso/deepseek-r1-distill-qwen-32b: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 cortexso/deepseek-r1-distill-qwen-32b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/deepseek-r1-distill-qwen-32b:Q4_K_M

Use Docker

docker model run hf.co/cortexso/deepseek-r1-distill-qwen-32b:Q4_K_M

LM Studio
Jan

vLLM

How to use cortexso/deepseek-r1-distill-qwen-32b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortexso/deepseek-r1-distill-qwen-32b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cortexso/deepseek-r1-distill-qwen-32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cortexso/deepseek-r1-distill-qwen-32b:Q4_K_M

Ollama
How to use cortexso/deepseek-r1-distill-qwen-32b with Ollama:
```
ollama run hf.co/cortexso/deepseek-r1-distill-qwen-32b:Q4_K_M
```

Unsloth Studio

How to use cortexso/deepseek-r1-distill-qwen-32b 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 cortexso/deepseek-r1-distill-qwen-32b 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 cortexso/deepseek-r1-distill-qwen-32b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cortexso/deepseek-r1-distill-qwen-32b to start chatting

Docker Model Runner
How to use cortexso/deepseek-r1-distill-qwen-32b with Docker Model Runner:
```
docker model run hf.co/cortexso/deepseek-r1-distill-qwen-32b:Q4_K_M
```

Lemonade

How to use cortexso/deepseek-r1-distill-qwen-32b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cortexso/deepseek-r1-distill-qwen-32b:Q4_K_M

Run and chat with the model

lemonade run user.deepseek-r1-distill-qwen-32b-Q4_K_M

List all available models

lemonade list

Overview

DeepSeek developed and released the DeepSeek R1 Distill Qwen 32B model, a distilled version of the Qwen 32B language model. This is the most advanced and largest model in the DeepSeek R1 Distill family, offering unparalleled performance in text generation, dialogue optimization, and reasoning tasks.

The model is tailored for large-scale applications in conversational AI, research, enterprise solutions, and knowledge systems, delivering exceptional accuracy, efficiency, and safety at scale.

Variants

No	Variant	Cortex CLI command
1	Deepseek-r1-distill-qwen-32b-32b	`cortex run deepseek-r1-distill-qwen-32b:32b`

Use it with Jan (UI)

Install Jan using Quickstart
Use in Jan model Hub:
```
cortexso/deepseek-r1-distill-qwen-32b
```

Use it with Cortex (CLI)

Install Cortex using Quickstart

Run the model with command:

cortex run deepseek-r1-distill-qwen-32b

Credits

Author: DeepSeek
Converter: Homebrew
Original License: License
Papers: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Downloads last month: 90

GGUF

Model size

33B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Collection including cortexso/deepseek-r1-distill-qwen-32b

DeepSeek-R1

Collection

6 items • Updated Jan 23, 2025