Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.

Finetune Llama 3.3, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

A user-friendly Command-line/SDK tool that makes it quickly and easier to deploy open-source LLMs on AWS

AI-Powered PDF Summarizer is a tool that extracts and summarizes research papers from ArXiv PDFs using Ollama (Gemma 3 LLM). The system provides structured, downloadable summaries to help researchers and professionals quickly grasp key findings.

Gemma 3 [ Image-text-text ] [ video inference ] [ multi image chat ]

Get started with the new Gemma 3 model for on-device inference. Giving you the simplest steps to get started with AI on Android.

modify a language model's behavior by abliterating its weights.

multimodal chatbot

Chat with a character via reference images!

A Gradio interface that automatically transcribes YouTube videos using faster-whisper (small) and refines the transcription with ChatOllama (gemma3:12b).

Gemma3 Rag with ChromaDB RAG Nomic Embed Text embeddings

Leverage Gemma 3's capabilities using LitServe.

An AI-powered automated code review and refactoring tool built with LangChain. It scans Python, JavaScript, TypeScript, Java, C, and C++ for security vulnerabilities, refactors unsafe code, and creates a GitHub PR with improvements. Optional email reports provide findings and PR links. Secure your code effortlessly! 🔒

Grida bot running locally doing chors with LLM

Chatbot using gemma3

Go/Vue3/Gemma 3 27B API summarizer website, deployed on Render