Gemma 2 27B
Parameters
27B
Context Length
8K
Modality
Text
Architecture
Dense
KV Cache Rate
368 KB/tok
License
Gemma License
Release Date
27 Jun 2024
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.65 · Output: $0.65
Hardware Sizing
Precision
Context
Workload Memory: 17.95 GB
INT4 · 8K context
Base Weights: 12.57 GB
KV Cache: 2.88 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
17.9 / 21.6 GB usable
2x RTX 4090 24GB
17.9 / 43.2 GB usable · TP 2
Apple M4 24GB
17.9 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
Evaluation Benchmarks
Rank
#190
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1290 | 158 |
StackEval Archived | 0.724 | 15 |
QA Assistant Archived | 0.804 | 19 |
General Knowledge Reference | 0.752 | 23 |
Summarization Archived | 0.59 | 24 |
Rankings
Overall Rank
#190
Coding Rank
-
About Gemma 2 27B
Gemma 2 27B is Google's high-efficiency open foundation model designed for advanced reasoning, content creation, and enterprise NLP. It utilizes Grouped-Query Attention and logit soft-capping for high-precision inference on a single GPU.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
32
Key-Value Heads
16
Position Embedding
ROPE
Normalization
RMS Normalization
Activation Function
GELU
Dimensions
Hidden Dimension Size
4,096
Number of Layers
46
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.