Gemma 3 12B
Parameters
12B
Context Length
128K
Modality
Multimodal
Architecture
Dense
License
Gemma Terms of Use
Release Date
12 Mar 2025
Knowledge Cutoff
Aug 2024
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
2x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
128,000 tokens
Consumer
3x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#97
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1342 | 130 |
Rankings
Overall Rank
#97
Coding Rank
-
About Gemma 3 12B
Gemma 3 12B is a balanced multimodal open model from Google DeepMind designed for question answering, visual interpretation, and reasoning. Built with interleaved sliding-window attention, it supports text and image inputs over a 128K context window.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
48
Key-Value Heads
12
Attention Head Dimension
-
Position Embedding
ROPE
RoPE Theta
-
Sliding Window Attention
-
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
-
Dimensions
Hidden Dimension Size
3,072
Number of Layers
42
FFN Intermediate Size (Dense)
-
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
-
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.