VaultGemma: The world's most capable differentially private LLM
What changed
September 12, 2025 Amer Sinha, Software Engineer, and Ryan McKenna, Research Scientist, Google Research We introduce VaultGemma, the most capable model trained from scratch with differential privacy. As AI becomes more integrated into our lives, building it with privacy at its core is a critical frontier for the field. By developing and applying a new, robust understanding of the scaling laws for DP, we have successfully trained and released the largest open, DP-trained language model to date.
Why it matters
A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.
How it compares
Related prior coverage to compare against:
- MedGemma: Our most capable open models for health AI development
- Introducing GPT-5.4
- Llama 3
Sources
- VaultGemma: The world's most capable differentially private LLM (deepmind-blog)primary