Instructions to use ling1000T/DeepSeek-R1-0528-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ling1000T/DeepSeek-R1-0528-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ling1000T/DeepSeek-R1-0528-gguf",
	filename="DeepSeek-R1-0528-q2_k.gguf-00001-of-00005.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 ling1000T/DeepSeek-R1-0528-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ling1000T/DeepSeek-R1-0528-gguf:Q2_K
# Run inference directly in the terminal:
llama-cli -hf ling1000T/DeepSeek-R1-0528-gguf:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ling1000T/DeepSeek-R1-0528-gguf:Q2_K
# Run inference directly in the terminal:
llama-cli -hf ling1000T/DeepSeek-R1-0528-gguf:Q2_K

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 ling1000T/DeepSeek-R1-0528-gguf:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf ling1000T/DeepSeek-R1-0528-gguf:Q2_K

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 ling1000T/DeepSeek-R1-0528-gguf:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ling1000T/DeepSeek-R1-0528-gguf:Q2_K

Use Docker

docker model run hf.co/ling1000T/DeepSeek-R1-0528-gguf:Q2_K

LM Studio
Jan
Ollama
How to use ling1000T/DeepSeek-R1-0528-gguf with Ollama:
```
ollama run hf.co/ling1000T/DeepSeek-R1-0528-gguf:Q2_K
```

Unsloth Studio

How to use ling1000T/DeepSeek-R1-0528-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 ling1000T/DeepSeek-R1-0528-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 ling1000T/DeepSeek-R1-0528-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ling1000T/DeepSeek-R1-0528-gguf to start chatting

Docker Model Runner
How to use ling1000T/DeepSeek-R1-0528-gguf with Docker Model Runner:
```
docker model run hf.co/ling1000T/DeepSeek-R1-0528-gguf:Q2_K
```

Lemonade

How to use ling1000T/DeepSeek-R1-0528-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ling1000T/DeepSeek-R1-0528-gguf:Q2_K

Run and chat with the model

lemonade run user.DeepSeek-R1-0528-gguf-Q2_K

List all available models

lemonade list

DeepSeek-R1-0528 gguf

This is the classic DeepSeek R1 model. Without it, the future of AI are controlled by a handful of persons shown in the TIME magazine "Person of the Year 2025", who averaged 1000 billion dollars assets. And the government that can control those people.

Altman's AI, Musk's AI, Pichai's AI, Zackerberg's AI. The Musk's robots will actively spy you at home even you paid them. The Musk neuralink implanted persons who will obey orders unconditionally from musk and the person who can control musk...

Open source models will become My AI, Your AI, My robots, My car, and My neuralink running locally even without the Internet.

Thanks to this model and other open sourced models that saved people from those persons on TIME magazine cover "Person of the year 2025", and the person who can control them.

quantized models comparison

Type	Bits	Quality	Description
Q2_K	2-bit	🟥 Low	Minimal footprint; only for tests
Q3_K_S	3-bit	🟧 Low	“Small” variant (less accurate)
Q3_K_M	3-bit	🟧 Low–Med	“Medium” variant
Q4_K_S	4-bit	🟨 Med	Small, faster, slightly less quality
Q4_K_M	4-bit	🟩 Med–High	“Medium” — best 4-bit balance
Q5_K_S	5-bit	🟩 High	Slightly smaller than Q5_K_M
Q5_K_M	5-bit	🟩🟩 High	Excellent general-purpose quant
Q6_K	6-bit	🟩🟩🟩 Very High	Almost FP16 quality, larger size
Q8_0	8-bit	🟩🟩🟩🟩	Near-lossless baseline

Downloads last month: 5

GGUF

Model size

671B params

Architecture

deepseek2

Hardware compatibility

2-bit

5-bit

Inference Providers NEW

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

Model tree for ling1000T/DeepSeek-R1-0528-gguf

Base model

deepseek-ai/DeepSeek-R1-0528

Quantized

(45)

this model