Modelpublic

CompiwerAI/Mtrini-SVL-1.1-GGUF

sourceHugging Faceapache-2.0updated 22h agoView on Hugging Face

0likes149downloads

Model Card

🐪 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

text

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