Gemma 3n E2B IT
Active Parameters
6B
Context Length
33K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
Google Gemma License
Release Date
20 May 2025
Knowledge Cutoff
Jun 2024
API Pricing (per 1M)
Input: $0.00 · Output: $0.00
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
1x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
32,768 tokens
Consumer
1x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#209
| Benchmark | Score | Rank |
|---|---|---|
Professional Knowledge | 0.405 | 60 |
Graduate-Level QA | 0.248 | 124 |
Intelligence Index | 0.05 | 301 |
General Knowledge Reference | 0.601 | 32 |
Rankings
Overall Rank
#209
Coding Rank
-
About Gemma 3n E2B IT
Gemma 3n E2B IT is an edge-optimized multimodal model from Google built on the Matryoshka Transformer architecture for on-device deployment. It processes text, image, and audio inputs with native function calling over a 32K context window.
Technical Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
-
Key-Value Heads
-
Attention Head Dimension
-
Position Embedding
Absolute Position Embedding
RoPE Theta
-
Sliding Window Attention
-
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
-
Dimensions
Auxiliary Parameters
-
Hidden Dimension Size
2,560
Number of Layers
30
FFN Intermediate Size (Dense)
-
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
-
Mixture of Experts
Total Expert Parameters
2.0B
Number of Experts
-
Active Experts
-
Shared Experts
-
FFN Intermediate Size (per Expert)
-
Dense Layers Before MoE
-
About Gemma 3
Gemma 3 is a family of open, lightweight models from Google. It introduces multimodal image and text processing, supports over 140 languages, and features extended context windows up to 128K tokens. Models are available in multiple parameter sizes for diverse applications.