Brain tracker that won't blow smoke up your ass. Gemma 4, Android, fully local.
Local-first AI clipping studio - turn long videos into ready-to-post vertical Shorts entirely on your own PC. Multimodal clip detection, speaker-aware face tracking, editable captions, AI edit chat. No cloud AI, no fees.
GEMMA-CLI A remarkably fast, secure, and completely local terminal user interface for Google's Gemma models.
Running LTX‑2 19B AI Model: Image/Audio-to-Video Locally on Intel Arc (XPU) GPU & CPU
Multimodal AI platform powered by Gemma for text, image understanding, function calling, local inference, and agentic workflows.
BioGemma — Google Gemma 3 1B fine-tuned on medical/biomedical corpus for clinical NLP tasks
One-click installer for Google Gemma 4 12B — optimized to run on 8GB laptops, 1M context, native multimodal. No terminal. Win/Mac, MIT.
This project presents a medical question–answering language model built by fine-tuning Google Gemma-2-2B-IT using LoRA (Low-Rank Adaptation) 🧠⚕️. The primary objective is to adapt a general-purpose large language model to the healthcare domain in a parameter-efficient, reproducible, and resource-aware manner.
💎 AI-powered Business Intelligence platform that transforms business CSVs into dashboards, forecasts, AI reports, and smart invoices using Google Gemma 4.
A practice-first platform helping non-technical business owners master AI prompting through interactive coaching, comparison tools, and hands-on agent simulations.
Gemma is a family of lightweight, state-of-the-art open models built from the same research and technology used to create the Gemini models.
Hands-on benchmark of Google Gemma 4 in LM Studio, with prompts, Gradio evaluator, saved outputs, and a published companion report.
Ghost Job Detector is a production-ready Next.js web app that helps job seekers analyze job posts using AI before applying.
Gemma 4 — Free Online Multimodal AI Platform | Text, Image & Audio Understanding | Powered by Google's Open-Source Gemma 4 Models
This is a sample notebook that can be used for exploring the fine-tuning of LLM using Unsloth Library. The LLM used for the experimentation is Google Gemma.
Gemma-2b-it LLM has been finetuned on a dataset of Python codes, enabling it to proficiently learn Python syntax and assist in debugging tasks, offering valuable guidance to programmers.
🧪 70-test, 6-model AI benchmark: Gemma 4 vs Gemini Pro vs Flash vs Qwen. 420 verified runs across 13 categories. All prompts, rubrics, runner code & raw results included. Code executed, constraints verified, prompt injection confirmed on Vertex AI Studio.
Use Google Gemma with Gradio Chat
"Flipping mass surveillance to protect the public: A creator-first AI tool that monitors the web for stolen IP and automates legal takedowns."
Add a description, image, and links to the google-gemma topic page so that developers can more easily learn about it.
To associate your repository with the google-gemma topic, visit your repo's landing page and select "manage topics."