Overview
Chrome’s Built-in AI is a suite of on-device APIs that provide powerful AI capabilities while respecting your privacy.Gemini Nano
Google’s efficient on-device language model
On-Device Processing
All AI runs locally - no cloud required
Privacy First
Your data never leaves your device
No API Keys
Works out of the box without accounts
What is Gemini Nano?
Gemini Nano is Google’s most efficient AI model, specifically designed to run on-device:- Technical Specs
- Capabilities
- Privacy Benefits
Model Architecture:
- Optimized transformer architecture
- ~1.8 billion parameters
- Context window: 1024 tokens
- Output languages: English, Spanish, Japanese
- Runs on CPU or GPU
- Typical response time: 1-3 seconds
- Memory usage: ~1.5-2GB when loaded
- Model size: ~1.5GB download
- GPU: 4GB+ VRAM (recommended)
- CPU: 16GB+ RAM with 4+ cores
- Supports both x86 and ARM architectures
Available APIs
Chrome provides specialized APIs for different AI tasks, all powered by Gemini Nano:1. Prompt API (LanguageModel)
The core conversational AI interface for general-purpose text generation.temperature(0-2): Higher = more creative, lower = more focusedtopK(1-128): Number of top tokens to consider (affects diversity)outputLanguage: Output language code (en,es,ja)
2. Summarizer API
Specialized API for creating concise summaries of long text.tldr: Concise one-paragraph summarykey-points: Bullet list of main ideasteaser: Short engaging previewheadline: Single-sentence summary
plain-text: Clean text without formattingmarkdown: Formatted with markdown syntax
short: ~50-100 wordsmedium: ~100-200 wordslong: ~200-300 words
3. Translator API
Translate text between 100+ languages, completely offline.- European: English, Spanish, French, German, Italian, Portuguese, Dutch, Polish, Russian, Greek
- Asian: Chinese, Japanese, Korean, Hindi, Thai, Vietnamese, Indonesian
- Middle Eastern: Arabic, Hebrew, Turkish, Farsi
- And many more…
4. Rewriter API
Rewrite and refine text with different tones and styles.as-is: Keep original toneformal: Professional, polishedcasual: Friendly, conversational
as-is: Keep original formatplain-text: Remove formattingmarkdown: Add markdown formatting
as-is: Keep original lengthshorter: More conciselonger: More detailed
5. Writer API
Generate new content from scratch based on prompts.6. Language Detector API
Identify the language of any text with confidence scores.Configuration
Customize Chrome AI behavior in VAssist settings:Setup Requirements
To use Chrome’s Built-in AI, you need:Chrome Version
Chrome 138 or newerCheck your version at
chrome://versionUpdate at chrome://settings/help if neededEnable Flags
Required Chrome FlagsVisit these URLs and enable each flag:
-
chrome://flags/#optimization-guide-on-device-model→ Enabled BypassPerfRequirement -
chrome://flags/#prompt-api-for-gemini-nano→ Enabled -
chrome://flags/#prompt-api-for-gemini-nano-multimodal-input→ Enabled (for voice/image features) -
chrome://flags/#writer-api-for-gemini-nano→ Enabled -
chrome://flags/#rewriter-api-for-gemini-nano→ Enabled -
chrome://flags/#summarization-api-for-gemini-nano→ Enabled -
chrome://flags/#translation-api→ Enabled -
chrome://flags/#language-detection-api→ Enabled
Download Model
Download Gemini Nano (~1.5GB)
- Visit
chrome://components - Find “Optimization Guide On Device Model”
- Click “Check for update”
- Wait for download to complete
- Monitor at
chrome://on-device-internals/
See the Installation Guide for detailed setup instructions with screenshots.
Troubleshooting
Model Not Downloading
Model Not Downloading
Symptoms:
- “Check for update” does nothing
- Component not appearing in chrome://components
- Verify all Chrome flags are enabled
- Restart Chrome completely (not just relaunch)
- Toggle flags off and on, then restart again
- Check free disk space (~2GB needed)
- Try unmetered network connection
API Not Available
API Not Available
Symptoms:
LanguageModel is not defined- VAssist shows “Chrome AI not available”
- Confirm Chrome version 138+
- Verify all required flags enabled
- Restart browser after enabling flags
- Check chrome://on-device-internals/ for errors
- Try creating session manually in DevTools console
Context Window Full
Context Window Full
Symptoms:
- Error: “QuotaExceededError”
- Long conversations stop working
- Start a new conversation
- Enable “Temporary Chat” mode
- Reduce page context length
- Gemini Nano has 1024 token limit - this is normal
Performance Issues
Performance Issues
Symptoms:
- Slow response times
- Browser freezing
- Close other tabs/applications
- Check hardware meets minimum requirements:
- 4GB+ VRAM (GPU) OR 16GB+ RAM (CPU)
- Disable other Chrome extensions temporarily
- Monitor Task Manager for memory usage
Privacy Benefits
Running AI on-device provides significant privacy advantages:No Server Communication
Zero network requests for AI processing. Your data stays on your device.
No Usage Tracking
Chrome doesn’t log or analyze your prompts and responses.
Offline Capable
Works without internet after model download. Perfect for sensitive work.
Regulatory Compliance
Automatic GDPR, HIPAA, and data protection compliance through on-device processing.
Unlike cloud-based AI services, Chrome’s Built-in AI ensures your conversations, documents, and personal information never leave your computer.
Performance Characteristics
- Speed
- Resource Usage
- Scalability
Typical Response Times (varies by hardware):
Factors Affecting Speed:
| Task | GPU | CPU |
|---|---|---|
| Short prompt (10 words) | 0.5-1s | 1-2s |
| Medium prompt (50 words) | 1-2s | 2-4s |
| Long prompt (200 words) | 2-4s | 4-8s |
| Streaming (first token) | 0.3-0.5s | 0.5-1s |
- Hardware specs (GPU vs CPU)
- Prompt complexity
- Context length
- Concurrent browser activity
Comparison with Cloud AI
| Feature | Chrome Built-in AI | Cloud AI (GPT, Claude) |
|---|---|---|
| Privacy | ✅ 100% local | ❌ Data sent to servers |
| Speed | ✅ Fast (local) | ⚠️ Network dependent |
| Offline | ✅ Works offline | ❌ Requires internet |
| Cost | ✅ Free | ❌ API costs |
| Setup | ⚠️ Initial setup | ✅ Just API key |
| Capabilities | ⚠️ Good for most tasks | ✅ More advanced |
| Context Window | ⚠️ 1024 tokens | ✅ 8k-200k tokens |
| Updates | ⚠️ Via Chrome updates | ✅ Continuous |
Next Steps
Installation
Set up Chrome AI flags and download Gemini Nano
Configuration
Customize AI settings and behavior
AI Toolbar
Explore AI-powered text and image tools
Chat Interface
Learn about conversational AI features