Instructions to use pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-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 pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-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 pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0

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 pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0

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 pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0

Use Docker

docker model run hf.co/pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0

LM Studio
Jan

vLLM

How to use pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-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": "pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0

Ollama
How to use pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF with Ollama:
```
ollama run hf.co/pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0
```
Unsloth Desktop
Docker Model Runner
How to use pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF with Docker Model Runner:
```
docker model run hf.co/pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0
```

Lemonade

How to use pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF:Q4_0

Run and chat with the model

lemonade run user.DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF-Q4_0

List all available models

lemonade list

Atomic Chat

Original model: https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct

Tested on Snapdragon X Elite with LM Studio 0.3.2 ARM64 Technology Preview https://lmstudio.ai/snapdragon

Avg answer Speed: 24 tok/s

LM Studio Settings:

Before System: <|im_start|>system\n
After System: <|im_end|>\n
Before User: <|im_start|>user\n
After User: <|im_end|>\n
Before Assistant: <|im_start|>assistant\n
After Assistant: <|im_end|>\n

Downloads last month: 60

GGUF

Model size

16B params

Architecture

deepseek2

Hardware compatibility

4-bit

Model tree for pipilok/DeepSeek-Coder-V2-Lite-Instruct-Q4_0_4_8-GGUF

Base model

deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct

Quantized

(66)

this model