Instructions to use LiteMind/YutaLM-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiteMind/YutaLM-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LiteMind/YutaLM-GGUF",
	filename="YutaLM-Q4.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use LiteMind/YutaLM-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LiteMind/YutaLM-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LiteMind/YutaLM-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 LiteMind/YutaLM-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LiteMind/YutaLM-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 LiteMind/YutaLM-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LiteMind/YutaLM-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 LiteMind/YutaLM-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LiteMind/YutaLM-GGUF:Q4_K_M

Use Docker

docker model run hf.co/LiteMind/YutaLM-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use LiteMind/YutaLM-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiteMind/YutaLM-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": "LiteMind/YutaLM-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiteMind/YutaLM-GGUF:Q4_K_M

Ollama
How to use LiteMind/YutaLM-GGUF with Ollama:
```
ollama run hf.co/LiteMind/YutaLM-GGUF:Q4_K_M
```

Unsloth Studio new

How to use LiteMind/YutaLM-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 LiteMind/YutaLM-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 LiteMind/YutaLM-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LiteMind/YutaLM-GGUF to start chatting

Docker Model Runner
How to use LiteMind/YutaLM-GGUF with Docker Model Runner:
```
docker model run hf.co/LiteMind/YutaLM-GGUF:Q4_K_M
```

Lemonade

How to use LiteMind/YutaLM-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LiteMind/YutaLM-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.YutaLM-GGUF-Q4_K_M

List all available models

lemonade list

YutaLM v1.0 DEMO - Private Local AI Assistant for Android

YutaLM v1.0 DEMO: Your Private AI Assistant - 100% Local, 100% Private

A cutting-edge 350M parameter AI model with a dedicated Android runtime for immersive RolePlay experiences

Download App (APK) · Contact Us · Official Website

What is YutaLM v1.0 DEMO?
Why YutaLM v1.0 DEMO?
Key Features
Installation
Requirements
Usage
Available Characters
Contributing
Contact

What is YutaLM v1.0 DEMO?

YutaLM v1.0 DEMO is a comprehensive AI system that combines a 350M parameter language model with a dedicated Android runtime, specifically designed for immersive and engaging RolePlay experiences. The entire system runs locally on your device, ensuring absolute privacy with zero data sent to any servers.

Unlike generic AI models that require complex setup and technical knowledge, YutaLM v1.0 DEMO comes as a complete Android application ready to use out of the box. It features an elegant user interface, advanced conversation management, and character customization tools - all unified in a seamless, polished experience.

Why YutaLM v1.0 DEMO?

Feature	YutaLM v1.0 DEMO	Traditional Solutions
Custom Model	350M parameter model optimized for RolePlay	Generic models not specialized
Android App	Dedicated runtime, ready to use	Requires complex setup
Privacy	100% local - No internet required	Data sent to cloud servers
English Support	Native English understanding	Limited or translated support
Ease of Use	Install and play instantly	Technical knowledge required
Ready Characters	16+ pre-built characters	Manual setup needed

Key Features

350M Parameter Model Optimized for RolePlay

YutaLM v1.0 DEMO is built on a 350M parameter language model specifically trained and fine-tuned for RolePlay interactions. This size provides the perfect balance between response quality and performance efficiency on mobile devices, delivering intelligent and context-aware replies across various conversation scenarios and narrative styles.

Dedicated Android Runtime

Unlike traditional models that require complex configurations, YutaLM v1.0 DEMO comes as a complete Android application ready for immediate use. The app includes an elegant and intuitive user interface, advanced conversation management system, and character customization tools - all unified in a seamless, professional experience that just works.

Absolute Privacy

YutaLM v1.0 DEMO is designed from the ground up to protect your privacy. The app doesn't require an internet connection to function, which means all your conversations stay on your device. No servers tracking your activity, no ads extracting your data, no third parties involved. You have complete control over your data.

Native English Support

Built with Western audiences in mind, YutaLM provides natural and fluent English conversations. The model understands context, idioms, and cultural nuances, delivering responses that feel authentic and human-like in everyday interactions.

16+ Diverse RolePlay Characters

The app features a rich library of pre-built virtual characters ready to use, ranging from friendly and enthusiastic companions to serious and professional personas, and adventurous characters for exciting text-based adventures. Each character has its own memory and history, making every conversation a unique experience.

Optimized Performance and Efficiency

The application is optimized to run smoothly across a wide range of Android devices, from mid-range to flagship phones. Resource consumption is balanced to preserve battery life while maintaining responsive performance even in full local mode.

Installation

Download and Install

Download the APK from: https://litemind.infinityfreeapp.com/mobile.html
Go to Settings > Security > Enable "Install from unknown sources"
Tap the downloaded APK file and complete the installation
Open the app, choose your favorite character, and start chatting!

Requirements

Minimum Requirements

Requirement	Value
Operating System	Android 8.0 (API 26) or higher
RAM	4GB RAM
Storage	500MB
Processor	ARM64 (AArch64)

Recommended Specifications

Requirement	Optimal Value
Operating System	Android 10+
RAM	6GB-8GB RAM
Storage	1GB+
Processor	Modern chipset (Snapdragon 7xx/8xx or equivalent)

Usage

Step 1: Choose Your Character

When you open the app, you will find a list of available characters. Browse through the characters and choose one that matches your mood and needs. Each character has a brief description to help you understand their personality and style.

Step 2: Start the Conversation

Tap on your chosen character and start chatting. You can engage in casual conversation, request collaborative story writing, or dive into interactive text-based adventures.

Step 3: Customize Your Experience

Use the app settings to customize the display, conversation memory, and response style according to your preferences.

Available Characters

YutaLM v1.0 DEMO features over 16 diverse virtual characters including:

Friendly Characters: Energetic companions to help with your day
Adventure Characters: Partners in exciting journeys and fantasies
Educational Characters: Patient teachers who answer your questions
Creative Characters: Writers and creative assistants
Advisors: Practical personas for deep discussions and conversations

New characters are being added regularly. Check back for updates.

Contributing

We welcome contributions to help improve and develop YutaLM v1.0 DEMO!

Bug Reports: Encountered an issue? Let us know
Feature Suggestions: Have a great idea? Share it with us
Code Contributions: For developers, review the code and suggest improvements

Contact

Email: litemind.ai@gmail.com
WhatsApp: +218 91 296 9312
Official Website: litemind.infinityfreeapp.com

Made with love by

LiteMind AI

Abdul Rahman Ahmed

Software Developer and AI Enthusiast

If you enjoyed YutaLM v1.0 DEMO, share it with your friends!

Downloads last month: 59

GGUF

Model size

0.4B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

LiteMind
/

YutaLM-GGUF