Instructions to use CompiwerAI/Mtrini-SVL-1.1-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 CompiwerAI/Mtrini-SVL-1.1-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 CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16

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 CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16

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 CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16

Use Docker

docker model run hf.co/CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16

LM Studio
Jan
Ollama
How to use CompiwerAI/Mtrini-SVL-1.1-GGUF with Ollama:
```
ollama run hf.co/CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16
```
Unsloth Desktop

How to use CompiwerAI/Mtrini-SVL-1.1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16

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": "CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use CompiwerAI/Mtrini-SVL-1.1-GGUF with Docker Model Runner:
```
docker model run hf.co/CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16
```

Lemonade

How to use CompiwerAI/Mtrini-SVL-1.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16

Run and chat with the model

lemonade run user.Mtrini-SVL-1.1-GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use CompiwerAI/Mtrini-SVL-1.1-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 CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16

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 CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use CompiwerAI/Mtrini-SVL-1.1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16

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 "CompiwerAI/Mtrini-SVL-1.1-GGUF:BF16" \
  --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"

🐪 Mtrini-SVL-1.1-GGUF

Mtrini, but local.

This repository contains the GGUF version of Mtrini-SVL-1.1 for local inference with compatible GGUF runtimes.

No API.

No cloud.

Just Mtrini running on your machine. 🐪

🧠 What is Mtrini?

Mtrini-SVL-1.1 is an ~8B open-weight model developed by Compiwer AI and based on Qwen3-VL-8B-Instruct.

It focuses on:

🧠 Reasoning
💻 Coding
🧮 Mathematics
🇲🇦 Moroccan Darija
🌍 Multilingual tasks

🔄 SVL

Self-Verifying Loop

Generate
   ↓
Verify
   ↓
Improve
   ↓
Repeat 🔄

SVL is Compiwer AI's approach to encouraging models to check and refine their responses.

📦 GGUF

GGUF makes Mtrini suitable for compatible local inference software such as:

llama.cpp
LM Studio
KoboldCpp
Other GGUF-compatible runtimes

Check your runtime's Qwen3-VL support before running the model.

⚡ Model Information
Property	Value
Model	Mtrini-SVL-1.1
Format	GGUF
Base	Qwen3-VL-8B-Instruct
Architecture	Qwen3-VL
Parameters	~8B
Original Precision	BF16
Developer	Compiwer AI
Origin	🇲🇦 Salé, Morocco
🚀 llama.cpp

Example:

llama-cli \
  -m Mtrini-SVL-1.1-BF16.gguf \
  -p "Explain artificial intelligence in Moroccan Darija."

Your exact command may vary depending on your llama.cpp version and hardware.

💻 Run Mtrini Locally

The GGUF release is intended for:

Local AI • Offline AI • Coding • Reasoning • Darija • Research

Quantized versions can reduce memory requirements and make local inference more accessible.

⚠️ Don't Trust the Camel Too Much

Mtrini can still hallucinate.

It can get math wrong.

It can write broken code.

It can misunderstand Darija.

And sometimes it will say something with 100% confidence while being 100% wrong. 💀

Always verify important outputs.

🇲🇦 From Salé to the World

Mtrini is developed by Compiwer AI, an independent AI project focused on accessible open AI systems.

Building AI For Everyone.

🇲🇦 Salé, Morocco → 🌍 Open Source AI

Downloads last month: 149

GGUF

Model size

8B params

Architecture

qwen3vl

Hardware compatibility

16-bit

Inference Providers NEW

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

Model tree for CompiwerAI/Mtrini-SVL-1.1-GGUF

Base model

Qwen/Qwen3-VL-8B-Instruct

Finetuned

CompiwerAI/Mtrini-SVL-1.1-Merged

Quantized

(1)

this model