Instructions to use azrouisghi/azrou-modeles with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use azrouisghi/azrou-modeles 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 azrouisghi/azrou-modeles:Q8_0
# Run inference directly in the terminal:
llama cli -hf azrouisghi/azrou-modeles:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf azrouisghi/azrou-modeles:Q8_0
# Run inference directly in the terminal:
llama cli -hf azrouisghi/azrou-modeles:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf azrouisghi/azrou-modeles:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf azrouisghi/azrou-modeles:Q8_0

Use Docker

docker model run hf.co/azrouisghi/azrou-modeles:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use azrouisghi/azrou-modeles with Ollama:
```
ollama run hf.co/azrouisghi/azrou-modeles:Q8_0
```
Unsloth Desktop

How to use azrouisghi/azrou-modeles with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf azrouisghi/azrou-modeles:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "azrouisghi/azrou-modeles:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use azrouisghi/azrou-modeles with Docker Model Runner:
```
docker model run hf.co/azrouisghi/azrou-modeles:Q8_0
```

Lemonade

How to use azrouisghi/azrou-modeles with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull azrouisghi/azrou-modeles:Q8_0

Run and chat with the model

lemonade run user.azrou-modeles-Q8_0

List all available models

lemonade list

Hermes Agent

How to use azrouisghi/azrou-modeles with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf azrouisghi/azrou-modeles:Q8_0

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 azrouisghi/azrou-modeles:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use azrouisghi/azrou-modeles with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf azrouisghi/azrou-modeles:Q8_0

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 "azrouisghi/azrou-modeles:Q8_0" \
  --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"

Modèles d'Azrou Voix

Modèles téléchargés par l'app Azrou Voix et utilisés sur le téléphone, sans connexion. Aucune donnée de la personne ne sort du téléphone.

Fichier	Rôle	Origine	Licence
`azrou-agent-qwen3-0.6b-q8_0.gguf`	Choisit l'action d'Azrou à partir d'une phrase (forme compacte `action;clé=valeur`)	Qwen3-0.6B, affiné par LoRA sur des phrases françaises	Apache 2.0
`azrou-stt-fr.tar.bz2`	Reconnaissance vocale française en continu (encodeur et joiner int8, décodeur, jetons)	sherpa-onnx, streaming zipformer fr 2023-04-14 (k2-fsa)	Apache 2.0
`azrou-tts-st.tar.bz2`	Voix d'Azrou (Supertonic 3, int8 ; voix 2 et 6 utilisées)	Supertonic 3 (Supertone), via sherpa-onnx	Code MIT, modèle OpenRAIL-M
`azrou-tts-upmc.tar.bz2`	Voix Jessica et Pierre (Piper, int8, prononciation française seule)	Piper fr_FR-upmc-medium	CC BY-SA 4.0 (données UPMC, MaryTTS)
`azrou-tts-tom.tar.bz2`	Voix Tom (Piper, int8)	Piper fr_FR-tom-medium (Tjiho)	AGPL 3.0
`azrou-tts-tjiho2.tar.bz2`	Voix Tjiho (Piper, int8)	Piper fr_FR-tjiho-model2, https://github.com/tjiho/French-tts-model-piper	AGPL 3.0

L'agent ne fait que proposer une action ; l'app la vérifie avant d'agir. Il n'écrit jamais de réponse à la personne.

Chaque archive garde la licence et la fiche de son modèle d'origine. Les voix Piper incluent les données de prononciation d'espeak-ng réduites au français (GPL 3.0, https://github.com/espeak-ng/espeak-ng).

Downloads last month: 25

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

8-bit

Inference Providers NEW

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