# Gemma 3 1B / 4B / 12B / 27B: Google'ın 256K Vocab + Multimodal (4B+)

> Source: https://sukruyusufkaya.com/learn/fine-tuning-cookbook/ftc-gemma-3-1b-4b-12b-27b-recipe
> Updated: 2026-08-23T06:33:32.554Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part III — Small Open Models (1B–8B)
**TLDR:** Gemma 3 — Google'ın 2025 açık modelleri. 256K vocab (TR-friendly), 4B+ multimodal (SigLIP vision tower), GeGLU activation, RMSNorm, 128K context, ShieldGemma safety classifier. RTX 4090'da Gemma 3 4B/12B QLoRA. system role yok (user'a prepend), Gemma 3 ToS dikkati.