Google logo

Gemma 3n E2B Instructed LiteRT (Preview)

Google

Overview

Overview

Gemma 3n is a generative AI model optimized for use in everyday devices, such as phones, laptops, and tablets. It features innovations like Per-Layer Embedding (PLE) parameter caching and a MatFormer model architecture for reduced compute and memory. These models handle audio, text, and visual data, though this E4B preview currently supports text and vision input. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models, and is licensed for responsible commercial use.

Gemma 3n E2B Instructed LiteRT (Preview) was released on May 20, 2025.

Performance

Timeline

ReleasedUnknown
Knowledge CutoffUnknown

Specifications

Parameters
1.9B
License
Gemma
Training Data
Unknown
Tags
tuning:instruct

Benchmarks

Benchmarks

Gemma 3n E2B Instructed LiteRT (Preview) Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Wed Jan 21 2026
Notice missing or incorrect data?Start an Issue discussion→

Pricing

Pricing

Pricing, performance, and capabilities for Gemma 3n E2B Instructed LiteRT (Preview) across different providers:

No pricing information available for this model.

API Access

API Access Coming Soon

API access for Gemma 3n E2B Instructed LiteRT (Preview) will be available soon through our gateway.

Recent Posts

Recent Reviews

FAQ

Common questions about Gemma 3n E2B Instructed LiteRT (Preview)

Gemma 3n E2B Instructed LiteRT (Preview) was released on May 20, 2025 by Google.
Gemma 3n E2B Instructed LiteRT (Preview) was created by Google.
Gemma 3n E2B Instructed LiteRT (Preview) has 1.9 billion parameters.
Gemma 3n E2B Instructed LiteRT (Preview) is released under the Gemma license.
Gemma 3n E2B Instructed LiteRT (Preview) has a knowledge cutoff of June 2024. This means the model was trained on data up to this date and may not have information about events after this time.
Yes, Gemma 3n E2B Instructed LiteRT (Preview) is a multimodal model that can process both text and images as input.