Instructions to use TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF",
	filename="Qwen2.5-3B-Instruct-grpo-gmail-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 TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-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 TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-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 TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF with Ollama:
```
ollama run hf.co/TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M
```

Unsloth Studio new

How to use TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-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 TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-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 TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF to start chatting

Pi new

How to use TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF with Docker Model Runner:
```
docker model run hf.co/TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M
```

Lemonade

How to use TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-3B-Instruct-grpo-gmail-GGUF-Q4_K_M

List all available models

lemonade list

Qwen2.5-3B-Instruct GRPO Gmail (Q4_K_M GGUF)

Quantized version of TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail.

📥 Download & Run

```bash

Download (recommended - 3.5 GB)

huggingface-cli download TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail-GGUF Qwen2.5-3B-Instruct-grpo-gmail-Q4_K_M.gguf

Run with GPU

./llama-server -m Qwen2.5-3B-Instruct-grpo-gmail-Q4_K_M.gguf --port 8080 -ngl 99

Run on CPU

./llama-server -m Qwen2.5-3B-Instruct-grpo-gmail-Q4_K_M.gguf --port 8080 ```

⚙️ Quantization Info

Method: Q4_K_M (4-bit with K-means)
Size: ~2.3 GB (vs 6.7 GB F16)
Quality: 95%+ of F16 performance
Speed: 3-4x faster inference

🔗 Related Models

Full precision (F16): TurkishCodeMan/Qwen2.5-3B-Instruct-grpo-gmail
Base model: unsloth/Qwen2.5-3B-Instruct

🎯 Tool Calling Example

```python import requests

response = requests.post("http://localhost:8080/v1/chat/completions", json={ "messages": [ {"role": "system", "content": "You are a tool-calling assistant."}, {"role": "user", "content": "Send email to test@gmail.com about meeting tomorrow"} ], "temperature": 0.0, "max_tokens": 512 })

print(response.json()['choices'][0]['message']['content'])

Output: {"tool_calls": [{"function": "send_email", "arguments": {"to": ["test@gmail.com"], "subject": "Meeting Tomorrow", "body": "..."}}]}

```

📊 Training

SFT: 300 steps on 57 Gmail examples
GRPO: 300 steps reinforcement learning for tool calling accuracy
Final loss: 0.50 (excellent convergence)

🛠️ Supported Tools

`send_email`, `draft_email`, `read_email`, `search_emails`, `delete_email`, `modify_email`, `batch_modify_emails`, `batch_delete_emails`, `list_email_labels`, `create_label`, `update_label`, `delete_label`, `get_or_create_label`, `create_filter`, `list_filters`, `get_filter`, `delete_filter`, `create_filter_from_template`, `download_attachment`

Downloads last month: 21

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

Inference Providers NEW

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