Instructions to use GemMaroc/Qwen2.5-32B-Instruct-darija-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GemMaroc/Qwen2.5-32B-Instruct-darija-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GemMaroc/Qwen2.5-32B-Instruct-darija-gguf",
	filename="Qwen2.5-32B-Instruct-darija_ckpt-1500_f16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use GemMaroc/Qwen2.5-32B-Instruct-darija-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 GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16
# Run inference directly in the terminal:
llama cli -hf GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16
# Run inference directly in the terminal:
llama cli -hf GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16

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 GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16

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 GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16

Use Docker

docker model run hf.co/GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16

LM Studio
Jan

vLLM

How to use GemMaroc/Qwen2.5-32B-Instruct-darija-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GemMaroc/Qwen2.5-32B-Instruct-darija-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": "GemMaroc/Qwen2.5-32B-Instruct-darija-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16

Ollama
How to use GemMaroc/Qwen2.5-32B-Instruct-darija-gguf with Ollama:
```
ollama run hf.co/GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16
```

Unsloth Studio

How to use GemMaroc/Qwen2.5-32B-Instruct-darija-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 GemMaroc/Qwen2.5-32B-Instruct-darija-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 GemMaroc/Qwen2.5-32B-Instruct-darija-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GemMaroc/Qwen2.5-32B-Instruct-darija-gguf to start chatting

How to use GemMaroc/Qwen2.5-32B-Instruct-darija-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16

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": "GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GemMaroc/Qwen2.5-32B-Instruct-darija-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16

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 GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use GemMaroc/Qwen2.5-32B-Instruct-darija-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use GemMaroc/Qwen2.5-32B-Instruct-darija-gguf with Docker Model Runner:
```
docker model run hf.co/GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16
```

Lemonade

How to use GemMaroc/Qwen2.5-32B-Instruct-darija-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GemMaroc/Qwen2.5-32B-Instruct-darija-gguf:F16

Run and chat with the model

lemonade run user.Qwen2.5-32B-Instruct-darija-gguf-F16

List all available models

lemonade list

Qwen2.5-32B-Instruct-darija-gguf

This repository contains quantized versions of Qwen2.5-32B-Instruct-darija in GGUF format for efficient inference.

Available Quantizations

Quantization	Description	File Size	Use Case
`f16`	FP16 (no quantization)	62499.97 MB	Best quality, largest size
`0`	0	33207.78 MB	Quantized version

Usage

Using llama.cpp

# Download the desired quantization
wget https://huggingface.co/GemMaroc/Qwen2.5-32B-Instruct-darija-gguf/resolve/main/Qwen2.5-32B-Instruct-darija_ckpt-*_q8_0.gguf

# Run inference
./llama-cli -m Qwen2.5-32B-Instruct-darija_ckpt-*_q8_0.gguf -p "Your prompt here"

Using Python with llama-cpp-python

from llama_cpp import Llama

# Load the quantized model
llm = Llama(
    model_path="./Qwen2.5-32B-Instruct-darija_ckpt-*_q8_0.gguf",
    n_ctx=32768,  # Context length
    n_threads=8,  # Number of CPU threads
)

# Generate text
response = llm("Your prompt here", max_tokens=512)
print(response['choices'][0]['text'])

Model Information

Base Model: GemMaroc/Qwen2.5-32B-Instruct-darija
Quantization: Multiple GGUF formats available
Context Length: 32,768 tokens
Languages: Arabic (Moroccan Darija), English

Recommendations

For best quality: Use f16 (largest file size)
For balanced performance: Use q8_0 (recommended)
For resource-constrained environments: Use tq2_0 or tq1_0

Citation

If you use this model, please cite the original GemMaroc paper:

@misc{skiredj2025gemmarocunlockingdarijaproficiency,
      title={GemMaroc: Unlocking Darija Proficiency in LLMs with Minimal Data},
      author={Abderrahman Skiredj and Ferdaous Azhari and Houdaifa Atou and Nouamane Tazi and Ismail Berrada},
      year={2025},
      eprint={2505.17082},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.17082},
}