gemma4.devgemma4.dev
  • Models
  • Run Local
  • Deploy
  • Guides
Try Gemma 4 ↗
gemma4.devgemma4.dev

Gemma 4 Guides

Advanced guides for getting the most out of Gemma 4. Covers Thinking Mode, prompt formatting, function calling, and fine-tuning.

Quick Pick

Not sure where to start with Gemma 4?

arrow_forwardNew to Gemma 4 → Prompt Formattingarrow_forwardComplex reasoning → Thinking Modearrow_forwardStructured output → Function Callingarrow_forwardCustom model → QLoRA Fine-Tuning

All Guides

psychology

Thinking Mode

Intermediate

How Gemma 4's extended reasoning works and when to enable it

format_quote

Prompt Formatting

Beginner

Correct chat template and system prompt format for Gemma 4

code

Function Calling

Intermediate

Use Gemma 4's built-in tool calling for structured JSON output

model_training

QLoRA Fine-Tuning

Advanced

Fine-tune Gemma 4 with Unsloth QLoRA on consumer hardware

gemma4.devgemma4.dev

运行、部署和调试 Gemma 4 模型。专为快节奏开发者打造。

GitHubGitHubTwitterX (Twitter)Email
Models
  • Gemma 4 E2B
  • Gemma 4 E4B
  • Gemma 4 26B
  • Gemma 4 31B
  • Compare Models
Run Local
  • Ollama
  • Hugging Face
  • GGUF
  • LM Studio
  • llama.cpp
Deploy
  • vLLM
  • Gemini API
  • Vertex AI
  • Cloud Run
Guides & Help
  • Thinking Mode
  • Prompt Formatting
  • Function Calling
  • Error Fixes
© 2026 gemma4.dev All Rights Reserved.