Gemma 2 9B
Parameters
9B
Context Length
8K
Modality
Text
Architecture
Dense
License
Gemma License
Release Date
27 Jun 2024
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.03 · Output: $0.09
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
8,192 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
#171
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1267 | 146 |
StackEval Archived | 0.715 | 16 |
QA Assistant Archived | 0.822 | 18 |
General Knowledge Reference | 0.713 | 24 |
Summarization Archived | 0.582 | 26 |
Rankings
Overall Rank
#171
Coding Rank
-
About Gemma 2 9B
Gemma 2 9B is a versatile open language model by Google engineered for conversational AI, text generation, and code assistance. Trained on 8T tokens with knowledge distillation, it delivers strong performance across an 8K context window.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
32
Key-Value Heads
8
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
SwigLU
Dimensions
Hidden Dimension Size
2,304
Number of Layers
42
FFN Intermediate Size (Dense)
-
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
-
About Gemma 2
Gemma 2 is Google's family of open large language models, offering 2B, 9B, and 27B parameter sizes. Built upon the Gemma architecture, it incorporates innovations such as interleaved local and global attention, logit soft-capping for training stability, and Grouped Query Attention for inference efficiency. The smaller models leverage knowledge distillation.