Local LLM

AlexPechkin

About this app

Local LLM is a powerful, privacy-centric tool designed to run Large Language Models directly on your device. No cloud, no data collection, and no subscription required — just pure local AI performance.

Key Features:
• Multimodal Capabilities & Web Search: Send images and audio directly to your AI with support for multimodal Gemma 4 models in the LiteRT (.litert) format. Additionally, with your explicit confirmation, these models can search the web to fetch real-time information.
• GGUF Support: Import and run your favorite instruction-tuned LLMs in GGUF format (such as Gemma and more).
• Model Store: Browse and download developer-recommended models directly in the app — or import your own.
• Voice Input with Whisper or Gemma 4: Use Whisper or Gemma 4-based speech recognition to interact with your models hands-free, fully on-device.
• Ukrainian TTS & Text Reader: Enjoy a fully integrated text-to-speech reader powered by StyleTTS2 (by patriotyk), with native Ukrainian language support — no internet required.
• AI Translator Mode: Use your local models as a professional translator while keeping your content completely private.
• 100% Offline & Private: Your data never leaves your device. All processing is done locally, ensuring maximum privacy and security.

Why choose Local LLM?
• No API keys or internet connection required after model setup.
• Full control over your AI models and data.
• Perfect for developers, privacy enthusiasts, and anyone wanting to explore the world of local AI.

Important Note:
The app does not include pre-installed model files. Use the built-in Model Store to download recommended models, or import your own instruction-tuned GGUF files.

What’s new

Bug fixes.