GoogleGemma 3
Gemma 3 27B
Gemma 3's largest core vision-language checkpoint.
What the release provides
The 27B model accepts images and text, generates text, and has a shared 128K window. Instruction weights are published.Google Gemma 3 model card
How to use it well
Practical guidance. Review its benefit on tasks where smaller checkpoints fail, such as dense documents or multi-step questions. Compare completed answers and hardware use together. Keep a trace from extracted claims to their source passages or image regions.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | google/gemma-3-27b-it |