Multimodal encoder-decoder models based on Gemma 3 in 270M-270M, 1B-1B and 4B-4B sizes.
Released
Dec 18, 2025
Context window
131K tokens
Max output
32.8K tokens
Parameters
Not disclosed
Input price
Not disclosed
Output price
Not disclosed
Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.
Pricing
No first-party API. This is an open-weights release you can run yourself.
Specifications
- Developer
- Model type
- Multimodal
- Architecture
- Not disclosed
- Parameters
- Not disclosed
- Input
- Text Image
- Output
- Text
- Knowledge cutoff
- Aug 2024
- License
- Gemma Terms of Use
- API access
- No first-party API
- Capabilities
- Small LM Vision