Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.

A Framework of Small-scale Large Multimodal Models

A CLI to manage install and configure llama inference implemenation in multiple languages

A set of bash scripts to automate deployment of GGML/GGUF models [default: RWKV] with the use of KoboldCpp on Android - Termux

A simple Python script for running LLMs on Intel's Neural Processing Units (NPUs)

This application allows users to upload PDF files, process them, and ask questions about the content using a locally hosted language model. The system uses Retrieval-Augmented Generation (RAG) to provide accurate answers based on the uploaded PDFs.

A real-time offline voice-to-voice AI assistant built for Raspberry Pi

onenm_local_llm is a Flutter plugin that simplifies on-device language model inference on Android using llama.cpp. It removes the complexity of setting up native runtimes, model loading, and inference pipelines, so developers can integrate local AI into their apps through a simple API.

OpenVINO LLM Node.js C++ addon

Most simple and minimal code to run an LLM chatbot from HuggingFace hub with OpenVINO

An integrated AI suite combining intelligent PDF analysis, automated research capabilities, and multi-agent academic paper generation, powered by both cloud and local language models to streamline research and document processing workflows.

MindEase is a mental health assistant that combines IoT hardware with AI to provide emotional support. It uses an ESP32 for audio input/output and integrates with AI models and cloud services for natural language understanding and response generation.

An offline AI-powered chatbot built using Streamlit and TinyLlama. It responds to your messages in real-time without needing internet access. Great for experimenting with lightweight local language models.

Fine-tuning the Tiny Llama model to mimic my professor's writing style using the Llama Factory. The project involves data collection, preprocessing, preparation, fine-tuning, and evaluation.

Educational research demonstrating weight manipulation attacks in SafeTensors models. Proves format validation alone is insufficient for AI model security.

bot for Ministry of Planning, Development & Special Initiatives

Quantize TinyLlama-1.1B-Chat from PyTorch to CoreML (float16, int8, int4) for efficient on-device inference on iOS 18+.

📲 Create a local LLM server on Android using Python and llama.cpp for easy access to language models.

This project is a chat application with a web interface developed using Streamlit and a backend developed with FastAPI. Use LLM TinyLlama Model as chat assistant.

Terminal Commander AI is a smart, natural language terminal assistant that converts English instructions into safe, executable shell commands. It supports ROS operations, multi-terminal launching, command explanations, and history — powered by a local TinyLlama LLM.