Instructions to use snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-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 snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-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 snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-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 snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-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 snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-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": "snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M

Ollama
How to use snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF with Ollama:
```
ollama run hf.co/snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF with Docker Model Runner:
```
docker model run hf.co/snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M
```

Lemonade

How to use snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-R1-Distill-Qwen-1.5B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

🧣 SnugGGUF: DeepSeek-R1-Distill-Qwen-1.5B

Every model. Every quant. Always free. Always tested.

⚡ Quick Start

Ollama: ollama run snuggguf/deepseek-r1-1.5b

LM Studio: Search snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF in Discover → pick Q4_K_M for maximum speed.

📦 Available Quants

Quant	Size	Tested
Q4_K_M	~1.0 GB	✅ Verified locally with Ollama

More quants (Q5_K_M, Q6_K) coming soon.

✅ Verification

GGUF magic bytes verified during conversion ✅
File size integrity confirmed ✅
Local Ollama inference test passed ✅
Runs 100% offline — no internet required ✅

🧠 About This Model

This is a distilled version of DeepSeek-R1, optimized for local reasoning tasks. It's incredibly fast and fits easily on most hardware, making it perfect for quick logic checks and coding assistance.

🐾 About SnugGGUF

SnugGGUF quantizes every major open model — Qwen, DeepSeek, Mistral, Llama, Gemma, GLM, Nemotron, Kimi, gpt-oss and more.

Every file is inference-tested before going public. No broken quants. Ever.

View all SnugGGUF models →

Downloads last month: 383

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for snuggguf/DeepSeek-R1-Distill-Qwen-1.5B-GGUF

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Quantized

(258)

this model