Instructions to use gghfez/DeepSeek-R1-Zero-IQ2_KS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gghfez/DeepSeek-R1-Zero-IQ2_KS with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="gghfez/DeepSeek-R1-Zero-IQ2_KS",
	filename="DeepSeek-R1-Zero-IQ2_KS-00001-of-00005.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 gghfez/DeepSeek-R1-Zero-IQ2_KS with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gghfez/DeepSeek-R1-Zero-IQ2_KS:Q2_K
# Run inference directly in the terminal:
llama-cli -hf gghfez/DeepSeek-R1-Zero-IQ2_KS:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gghfez/DeepSeek-R1-Zero-IQ2_KS:Q2_K
# Run inference directly in the terminal:
llama-cli -hf gghfez/DeepSeek-R1-Zero-IQ2_KS: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 gghfez/DeepSeek-R1-Zero-IQ2_KS:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf gghfez/DeepSeek-R1-Zero-IQ2_KS: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 gghfez/DeepSeek-R1-Zero-IQ2_KS:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gghfez/DeepSeek-R1-Zero-IQ2_KS:Q2_K

Use Docker

docker model run hf.co/gghfez/DeepSeek-R1-Zero-IQ2_KS:Q2_K

LM Studio
Jan

vLLM

How to use gghfez/DeepSeek-R1-Zero-IQ2_KS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gghfez/DeepSeek-R1-Zero-IQ2_KS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gghfez/DeepSeek-R1-Zero-IQ2_KS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gghfez/DeepSeek-R1-Zero-IQ2_KS:Q2_K

Ollama
How to use gghfez/DeepSeek-R1-Zero-IQ2_KS with Ollama:
```
ollama run hf.co/gghfez/DeepSeek-R1-Zero-IQ2_KS:Q2_K
```

Unsloth Studio new

How to use gghfez/DeepSeek-R1-Zero-IQ2_KS 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 gghfez/DeepSeek-R1-Zero-IQ2_KS 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 gghfez/DeepSeek-R1-Zero-IQ2_KS to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gghfez/DeepSeek-R1-Zero-IQ2_KS to start chatting

Docker Model Runner
How to use gghfez/DeepSeek-R1-Zero-IQ2_KS with Docker Model Runner:
```
docker model run hf.co/gghfez/DeepSeek-R1-Zero-IQ2_KS:Q2_K
```

Lemonade

How to use gghfez/DeepSeek-R1-Zero-IQ2_KS with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gghfez/DeepSeek-R1-Zero-IQ2_KS:Q2_K

Run and chat with the model

lemonade run user.DeepSeek-R1-Zero-IQ2_KS-Q2_K

List all available models

lemonade list

`ik_llama.cpp` imatrix MLA Quantizations of deepseek-ai/DeepSeek-R1-Zero

This is an IQ2_KS quant of deepseek-ai/DeepSeek-R1-Zero using ubergarm's IQ2_KS recipe from ubergarm/DeepSeek-TNG-R1T2-Chimera-GGUF.

This quant collection REQUIRES ik_llama.cpp fork to support advanced non-linear SotA quants and Multi-Head Latent Attention (MLA). Do not download these big files and expect them to run on mainline vanilla llama.cpp, ollama, LM Studio, KoboldCpp, etc!

I've uploaded the converted BF16 weights gghfez/DeepSeek-R1-Zero-256x21B-BF16 if I, or anyone else wants to create similar quants in the future.

Note: I may be deleting gghfez/DeepSeek-R1-Zero-256x21B-BF16 shortly due to the new huggingface storage limits.

Downloads last month: 7

GGUF

Model size

672B params

Architecture

deepseek2

Hardware compatibility

2-bit

Model tree for gghfez/DeepSeek-R1-Zero-IQ2_KS

Base model

deepseek-ai/DeepSeek-R1-Zero

Quantized

(6)

this model

Collection including gghfez/DeepSeek-R1-Zero-IQ2_KS

ik_llama quants

Collection

8 items • Updated Mar 2 • 1

ik_llama.cpp imatrix MLA Quantizations of deepseek-ai/DeepSeek-R1-Zero

Model tree for gghfez/DeepSeek-R1-Zero-IQ2_KS

Collection including gghfez/DeepSeek-R1-Zero-IQ2_KS

`ik_llama.cpp` imatrix MLA Quantizations of deepseek-ai/DeepSeek-R1-Zero