GoogleReleased on May 20, 2025

Gemma 3n E2B Instructed LiteRT (Preview): API Pricing, Context Window & Benchmarks

Gemma 3n E2B Instructed LiteRT (Preview) is a language model from Google, released in May 2025, with multimodal input.

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

Gemma 3n E2B Instructed LiteRT (Preview) benchmarks

Rankings

Quality Tracker

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

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

llm-stats.com - Tue Jul 21 2026

Notice missing or incorrect data?

Gemma 3n E2B Instructed LiteRT (Preview) model size

Gemma 3n E2B Instructed LiteRT (Preview) has 1.9 billion parameters. See how it compares to other models in the same parameter range.

Parameters

1.9B

Small (<3B)

1.9B

1B7B70B405B

Gemma 3n E2B Instructed LiteRT (Preview) API

API availability not verified

API availability for Gemma 3n E2B Instructed LiteRT (Preview) has not been verified. It is not currently routed through the LLM Stats gateway.

Gemma 3n E2B Instructed LiteRT (Preview) latency

Gemma 3n E2B Instructed LiteRT (Preview) time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

Gemma 3n E2B Instructed LiteRT (Preview) examples

Recent arena outputs from Gemma 3n E2B Instructed LiteRT (Preview), picked from the highest-ranked matchups.

Gemma 3n E2B Instructed LiteRT (Preview) license

Gemma 3n E2B Instructed LiteRT (Preview) is released under the Gemma license, which permits commercial use, has 1.9B parameters, has a knowledge cutoff of June 2024.

License: Gemma; Commercial use allowed
Parameters: 1.9B
Knowledge cutoff: June 2024

Google Gemma Terms of Use

Gemma 3n E2B Instructed LiteRT (Preview) resources

Official sources for Gemma 3n E2B Instructed LiteRT (Preview): official playground, official launch post, source repository.

Gemma 3n E2B Instructed LiteRT (Preview) vs other models

The most-compared alternatives to Gemma 3n E2B Instructed LiteRT (Preview) are Phi 4 Mini, IBM Granite 4.0 Tiny Preview, Jamba 1.5 Mini. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Gemma 3n E2B Instructed LiteRT (Preview)

Models ranked just above and below Gemma 3n E2B Instructed LiteRT (Preview) by LLM Stats score.

Phi 4 Mini

Score pending

Details Compare

IBM Granite 4.0 Tiny Preview

Score pending

Details Compare

Jamba 1.5 Mini

Score pending

Details Compare

Llama 3.2 3B Instruct

Score pending

Details Compare

Qwen2.5-Coder 7B Instruct

Score pending

Details Compare

Gemma 3n E4B Instructed LiteRT Preview

Score pending

Details Compare

FAQ

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

When was Gemma 3n E2B Instructed LiteRT (Preview) released?

Gemma 3n E2B Instructed LiteRT (Preview) was released on May 20, 2025 by Google. This is the official Gemma 3n E2B Instructed LiteRT (Preview) release date tracked on LLM Stats.

How big is Gemma 3n E2B Instructed LiteRT (Preview)?

Gemma 3n E2B Instructed LiteRT (Preview) has 1.9 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Gemma 3n E2B Instructed LiteRT (Preview)?

Gemma 3n E2B Instructed LiteRT (Preview) was created by Google.

What is the license for Gemma 3n E2B Instructed LiteRT (Preview)?

Gemma 3n E2B Instructed LiteRT (Preview) is released under the Gemma license. This is an open-source / open-weight license that permits self-hosting.

What is the knowledge cutoff date for Gemma 3n E2B Instructed LiteRT (Preview)?

Gemma 3n E2B Instructed LiteRT (Preview) has a knowledge cutoff of June 2024, meaning it was trained on data up to that point and may not know about events after it.

Is Gemma 3n E2B Instructed LiteRT (Preview) multimodal?

Yes, Gemma 3n E2B Instructed LiteRT (Preview) is multimodal and can accept both text and images as input.

Where is the Gemma 3n E2B Instructed LiteRT (Preview) paper or technical report?

Gemma 3n E2B Instructed LiteRT (Preview) has a paper or technical report available at https://ai.google.dev/gemma/docs/gemma-3n. Use that source for architecture, training, release and evaluation details.

What models should I compare Gemma 3n E2B Instructed LiteRT (Preview) against?

Common Gemma 3n E2B Instructed LiteRT (Preview) comparisons include Gemma 3n E2B Instructed LiteRT (Preview) vs Phi 4 Mini, Gemma 3n E2B Instructed LiteRT (Preview) vs IBM Granite 4.0 Tiny Preview, Gemma 3n E2B Instructed LiteRT (Preview) vs Jamba 1.5 Mini. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.