Gemma 4 E2B
Gemma 4 E 2B is an open-source, multimodal model developed by Google, capable of handling text and image input and generating text output, with support for over 140 languages. It is well-suited for tasks like text generation, coding, and reasoning, featuring a Dense architecture and a context window of up to 131,072 tokens.
Input
Output
Context
131K
Max Output
1K
Parameters
5.1B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens512 tokens
Parameters5.1B
Release DateMar 2, 2026
Training CutoffJan 1, 2025
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImageAudio
Output Modalities
TextImageAudio
Capabilities
Benchmarks
Artificial Analysis
4.8%
HLE
15.0%
AA-LCR
43.3%
GPQA
20.8%
Tau2-Bench
38.0%
IFBench
20.9%
SciCode
4.5%
Tau2 Banking
7.2
Coding
9.7
Intelligence
3.0%
Terminal-Bench Hard
0.4%
Terminal-Bench 2.1
Estimated GPU Requirements for Gemma 4 E2B
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: Aug 6, 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.