Instructions to use truegleai/deepseek-coder-api with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use truegleai/deepseek-coder-api with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="truegleai/deepseek-coder-api",
	filename="DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.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 truegleai/deepseek-coder-api with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf truegleai/deepseek-coder-api:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf truegleai/deepseek-coder-api:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf truegleai/deepseek-coder-api:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf truegleai/deepseek-coder-api: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 truegleai/deepseek-coder-api:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf truegleai/deepseek-coder-api: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 truegleai/deepseek-coder-api:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf truegleai/deepseek-coder-api:Q4_K_M

Use Docker

docker model run hf.co/truegleai/deepseek-coder-api:Q4_K_M

LM Studio
Jan
Ollama
How to use truegleai/deepseek-coder-api with Ollama:
```
ollama run hf.co/truegleai/deepseek-coder-api:Q4_K_M
```

Unsloth Studio new

How to use truegleai/deepseek-coder-api 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 truegleai/deepseek-coder-api 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 truegleai/deepseek-coder-api to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for truegleai/deepseek-coder-api to start chatting

Docker Model Runner
How to use truegleai/deepseek-coder-api with Docker Model Runner:
```
docker model run hf.co/truegleai/deepseek-coder-api:Q4_K_M
```

Lemonade

How to use truegleai/deepseek-coder-api with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull truegleai/deepseek-coder-api:Q4_K_M

Run and chat with the model

lemonade run user.deepseek-coder-api-Q4_K_M

List all available models

lemonade list

🚀 o87Dev - Maximum Capacity Deployment

Strategy: Deploy the largest viable model (DeepSeek-Coder-V2-Lite-Instruct-16B-Q4_K_M) on Hugging Face's free CPU tier.

⚙️ Technical Details

Model: DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf (10.4GB)
Quantization: Q4_K_M (Optimal quality/size for free tier)
Loader: llama-cpp-python (CPU optimized)
Context: 2048 tokens (max for free tier stability)

📊 Performance Expectations

First load: ~60-120 seconds (model loads from disk)
Inference speed: ~2-5 tokens/second on CPU
Memory usage: ~12-14GB of 16GB available

🎯 Usage Tips

First request triggers model load (be patient)
Keep prompts under 500 tokens for best results
Use temperature 0.7-0.9 for creative tasks
Monitor memory usage in Space logs

🔗 Integration

This Space serves as the primary AI endpoint for the o87Dev local API server.

Downloads last month: 8

GGUF

Model size

16B params

Architecture

deepseek2

Hardware compatibility

4-bit

Inference Providers NEW

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