TL;DR : Gemma 4 models in Ollama carry RENDERER gemma4 , which Ollama 0.35.1 resolves per request to gemma4-small (the e2b/e4b template) or gemma4-large (12b, 26b, 31b). It decides by looking for e2b / e4b or 12b / 26b / 31b in the model's name, and if there is none, by parameter count against 12…
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass TouchGrass AI: turning an AI prompt into a reason to put my phone away I built TouchGrass AI , a small outdoor quest companion. You choose how much time you have, what kind of outing sounds good, and how much…
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built Study Buddy is an offline exam study partner I built for my friend Anushka , who is preparing for GATE . GATE has a huge syllabus, and she wanted quick answers and practice questions from her own notes. I…
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built A batchmate of mine, has campus placement drives coming up and wants practice with real interview questions about their own projects, not another generic list from the internet. So I built PlacePal , an…
