Gemma 3 12B
Gemma 3 12B It, developed by Google, is a multimodal chat model capable of handling text and image inputs and generating text outputs, with a context window of 32,768 tokens. It is well-suited for tasks such as question answering, summarization, and reasoning, and its open-source license allows for flexible deployment.
Input
Output
Context
131K
Max Output
8K
Parameters
12.2B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens8,192 tokens
Parameters12.2B
Release DateMar 1, 2025
Training CutoffAug 1, 2024
Licensegemma
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
4.8%
HLE
22.0%
AIME
34.9%
GPQA
17.4%
SciCode
85.3%
MATH 500
59.5%
MMLU Pro
18.3
Math
6.3
Coding
13.7%
LiveCodeBench
3.4
Intelligence
Estimated GPU Requirements for Gemma 3 12B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Google
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jul 17, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.