Skip to content
Gemma Documentation
Google Gemma Open Models
Search
Home
Get started
Models
Run
Fine-tune
Learn
Resources
Gemma Documentation
Home
Get started
Get started
Quickstart
Best practices
Text
Text
Inference
Reasoning
Tool calling
Multimodal
Multimodal
Vision overview
Image understanding
Video understanding
Audio understanding
Advanced
Advanced
Prompt formatting
Multi-Token Prediction
Quantization-Aware Training
Models
Models
Overview
Gemma 4
Gemma 4
Overview
Model card
Previous generations
Previous generations
Gemma 3
Gemma 2
Gemma
Variants
Variants
Gemma 3n
Gemma 3n
Overview
Model card
DiffusionGemma
DiffusionGemma
Overview
Model card
Diffusion explained
Generate output
FunctionGemma
FunctionGemma
Overview
Model card
Formatting and best practices
Function calling with HF
Full sequence
Fine-tuning
EmbeddingGemma
EmbeddingGemma
Overview
EmbeddingGemma model card
EmbeddingGemma 2 model card
Generate embeddings
Multimodal embeddings
Fine-tuning
Multimodal fine-tuning
PaliGemma
PaliGemma
Overview
PaliGemma model card
PaliGemma 2 model card
Prompting & system instructions
Generate output with Keras
Fine-tuning with JAX
ShieldGemma
ShieldGemma
Overview
ShieldGemma model card
ShieldGemma 2 model card
Research
Research
RecurrentGemma
RecurrentGemma
Overview
Model card
Generate output with JAX
Fine-tuning with JAX
DataGemma
Gemma Scope
Gemma APS
Releases
Run
Run
Overview
Local
Local
Ollama
llama.cpp
LM Studio
MLX
Hugging Face Transformers
Keras
LiteRT-LM
AI Edge Gallery
Serve
Serve
vLLM
SGLang
Gemini API
Google Cloud
Frameworks
Frameworks
LangChain
Unsloth
Fine-tune
Fine-tune
Overview
Foundations
Foundations
Best practices
Dataset formatting
Continued pre-training
Continued pre-training
Continued pre-training
Custom chat templates
Supervised fine-tuning
Supervised fine-tuning
(Q)LoRA
Full fine-tuning
MoE fine-tuning
Unused tokens
Multimodal fine-tuning
Multimodal fine-tuning
Vision fine-tuning
Audio fine-tuning
Reinforcement learning
Reinforcement learning
Preference optimization
Verifiable rewards
Deployment
Deployment
Scaling
Export
Unsloth
Gemma trainer skill
Learn
Learn
Overview
Interactive guides
Interactive guides
How LLMs work
Visual guides
Visual guides
Gemma 4
Gemma 4 12B
Multi-Token Prediction
DiffusionGemma
Gemma explained
Gemma explained
Overview
What's new in Gemma 2
RecurrentGemma
PaliGemma
What's new in Gemma 3
EmbeddingGemma
Resources
Resources
Overview
Demos & tools
Demos & tools
Gemma Skills
AIventure
Vision token budget
Embedding Draw Challenge
Legal
Legal
Gemma 4 license
Terms of use
Terms archive
Terms archive
Overview
April 1, 2024
February 21, 2024
Prohibited use
Intended use statement
Gemma
Our most capable open models
Run Gemma 4 locally with Ollama…
Explore
↵
Get started
Try in Google AI Studio
Explore models
Back to top