PaliGemma 2

Google DeepMind · 2024 · Vision-Language Model · USA / UK

Overview

Vision-language model. 3B, 10B, 28B. Fine-tuned for multiple visual tasks.

Vendor: Google DeepMind
Type: Vision-Language Model
Release year: 2024
Jurisdiction: USA / UK
CEO: Demis Hassabis
Key staffers: Demis Hassabis (CEO), Shane Legg (Co-founder), Koray Kavukcuoglu (CTO)
Deployment: Local (open weights)
Open source: Yes
Free tier: Yes
Subscription: Free (open weights)
Stock status: $400 (GOOGL, May 2026)
X: @GoogleDeepMind

5/5

AIDb v2.0 (rule-based): Capability 4/10 · Currency 4/10 · Access 8/10 · Significance 5/10 → 4.75

Computer-vision risks: dataset bias, domain shift, privacy concerns in images, and unreliable performance outside benchmark-like settings.

Last verified 2026-06-11 · Primary source ↗

“PaliGemma 2.” AIDb — The AI Database. Verified 2026-06-11. https://theaidatabase.com/m/google-deepmind-paligemma-2.html