G

gemma-3-12b-it

Multimodalby Google·Model page

gemma-3-12b-it is Google's 12.2B-parameter instruction-tuned Gemma 3 multimodal model for image and text understanding.

Max output

Most tokens the model can return in a single response.

16Ktokens
Share:

Base model

google/gemma-3-12b-pt
Author
G
Google
Organization · ✓
google
Details
Downloads2.3M
Likes761
AccessOpen Source
Context131K tokens
Input price$0.05 /1M
Output price$0.15 /1M
Taskimage-text-to-text
Parameters12.2B
Licensegemma
Librarytransformers
Knowledge cutoffAug 31, 2024
CreatedMar 1, 2025
UpdatedMar 21, 2025
View on Hugging Face
Benchmarks
Intelligence5.5
Coding5.8
Agentic0.3
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

gemma-3-12b-it — AI Model Details | Applied