LLM Hub-Local AI assistant

Experience the next generation of AI with LLMHub, the most powerful private AI assistant for iPhone and iPad. Run state-of-the-art Large Language Models (LLMs) completely on-device with zero data sharing, absolute privacy, and no internet connection required. Powered by the RunAnywhere SDK and optimized for Apple Silicon.

TEN POWERFUL ON-DEVICE TOOLS • SMART CHAT: Enjoy multi-turn conversations with context awareness, RAG memory, and optional text-to-speech auto-readout. Supports Text, Images, and Audio inputs. Powered by the RunAnywhere inference engine for maximum performance.

• [NEW] VIDEO GENERATOR: Generate high-quality cinematic videos from text or image prompts offline. Leverages optimized Stable Video Diffusion (SVD) and AnimateLCM models running locally on your hardware.

• [NEW] AI IMAGE UPSCALER: Enhance and upscale low-resolution photos up to 4x locally using Real-ESRGAN and UltraSharp models. Bring old or low-res images to life in stunning definition with zero privacy risk.

• IMAGE GENERATOR: Create beautiful visuals with Stable Diffusion. Optimized for the Apple Neural Engine (ANE) and Metal API for rapid, local image synthesis directly from text or image prompts.

• WRITING AID: Summarize long documents, rewrite copy, and improve grammar instantly. Process text locally without ever sending a single word to the cloud.

• TRANSLATOR (50+ Languages): Real-time, bidirectional translation for text, audio, and images (OCR). Perfect for secure, private communication while traveling or working.

• TRANSCRIBER: High-accuracy speech-to-text conversion using native iOS recognition. All audio processing happens on-device for total privacy.

• VIBECODE CREATOR: The ultimate AI personalization engine. Build, share, and use custom AI personas with deep-level behavioral instructions that persist across all your chats.

• CODE ASSISTANT: Generate, explain, and debug code using VibeCode-enhanced models like Gemma-4. Features local reasoning that understands your specific programming style.

• SCAM DETECTOR: Analyze suspicious messages and phishing images for risk. Get clear local assessments to keep your digital identity safe.

CUTTING-EDGE TECHNOLOGY STACK LLMHub is built specifically for iOS, leveraging the latest in mobile AI research:

• RunAnywhere SDK: A high-performance inference backend supporting GGUF, ONNX, and LiteRT formats with full Metal and Accelerate acceleration. • Apple Foundation Model Support: Seamlessly integrate with native Apple Intelligence foundation models for high-speed, system-level efficiency. • Metal & Neural Engine Optimization: Desktop-class performance on your iPhone and iPad via Apple Silicon (A-series and M-series chips).

FEATURED ON-DEVICE MODELS • Gemma-4 (Google): The latest in multimodal performance, featuring E2B and E4B variants for advanced text and vision tasks. • Apple Foundation Model: Apple's system-integrated intelligence optimized for your specific hardware. • Llama-3.2 (Meta): Powerful 1B and 3B reasoning models. • Phi-4 Mini (Microsoft): Optimized for mobile productivity. • Ministral (Mistral AI): High-performance multilingual support.

COMPLETE PRIVACY GUARANTEED • No Internet Required: All AI inference happens 100% on your device. • No Data Sharing: We never collect, store, or see your data. • No Accounts: Start using advanced AI immediately with no tracking or cloud uploads. • Open Source: Transparent and secure