Gemma 3 270M
Parameters
270M
Context Length
32K
Modality
Text
Architecture
Dense
KV Cache Rate
48 KB/tok
License
Apache 2.0
Release Date
14 Aug 2025
Knowledge Cutoff
Aug 2024
API Pricing (per 1M)
Self-hosted only
Hardware Sizing
Precision
Context
Workload Memory: 3.00 GB
INT4 · 8K context
Base Weights: 0.13 GB
KV Cache: 0.38 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
3.0 / 21.6 GB usable
1x RTX 3060 12GB
3.0 / 10.8 GB usable
Apple M4 24GB
3.0 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
Evaluation Benchmarks
Rank
#214
| Benchmark | Score | Rank |
|---|---|---|
Intelligence Index | 0.05 | 310 |
Rankings
Overall Rank
#214
Coding Rank
-
About Gemma 3 270M
Gemma 3 270M is Google's ultra-compact open-weights text model engineered for on-device classification, entity extraction, and edge routing. It features a 256K vocabulary supporting 140+ languages across a 32K token context window.
Technical Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
16
Key-Value Heads
16
Position Embedding
Absolute Position Embedding
Normalization
RMS Normalization
Activation Function
GELU
Dimensions
Hidden Dimension Size
1,024
Number of Layers
12
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.