# Gemma 3n E4B ![Organization](https://img.shields.io/badge/Org-Google-4285F4) ![Effective Params](https://img.shields.io/badge/Effective-4B-1f6feb) ![License](https://img.shields.io/badge/License-Gemma%20ToU-d29922) ![Weights](https://img.shields.io/badge/Weights-Open-2da44e) ![On--Device](https://img.shields.io/badge/Target-On--Device-2da44e) ![Released](https://img.shields.io/badge/Released-May%202025-555) > **Quick answer:** Gemma 3n E4B is Google's May 2025 on-device multimodal model with 4B effective parameters, scoring 61.6% on ARC-C, 75.0% on HumanEval, and 50.6% on MMLU-Pro. The "3n" architecture uses MatFormer nested structures for efficient on-device deployment while supporting text, image, and audio inputs. ## At a Glance **Where Gemma 3n E4B leads** - 75.0% HumanEval — excellent code completion at 4B effective params - Multimodal: text, image, and audio inputs on-device - MatFormer nested architecture — efficient on-device inference - Gemma Terms of Use with on-device distribution rights - Google I/O 2025 showcase model **Where it lags** - 4B effective params: below larger models on all benchmarks - 50.6% MMLU-Pro — moderate knowledge - On-device focus limits server-side competitive comparison - Gemma Terms of Use (not Apache 2.0) **Best for:** On-device multimodal applications; mobile AI with image + audio support; Google Pixel and Android on-device deployments. ## What Gemma 3n E4B Is Gemma 3n E4B (released May 20, 2025) is Google's on-device multimodal model line, announced at Google I/O 2025. The "3n" designation refers to the new MatFormer-based nested architecture, designed for efficient on-device deployment on mobile and edge hardware. Unlike previous Gemma models (1B, 4B, etc. which have constant parameter counts), Gemma 3n E4B refers to "4 billion effective parameters" — the MatFormer architecture allows the model to dynamically adjust compute based on task complexity. The model supports text, image, and audio inputs — making it the first Gemma model with audio understanding. This multimodal breadth at the 4B effective parameter scale is its primary differentiator from Llama 3.2 3B (text-only) and similar small models. ## Specifications | Field | Value | |---|---| | Organization | Google | | Effective parameters | 4B (MatFormer nested) | | License | Gemma Terms of Use | | HuggingFace | [google/gemma-3n-E4B-it](https://huggingface.co/google/gemma-3n-E4B-it) | | Release date | May 20, 2025 | | Knowledge cutoff | February 2025 | | Modality | Text + Vision + Audio | | Architecture | MatFormer (nested) | ## Pricing Open weights under Gemma Terms of Use — free to self-host. Optimised for on-device deployment. ## Public Benchmark Scores | Benchmark | Score | Source | Date | |---|---|---|---| | [ARC-C](/benchmarks/ai2-reasoning-challenge) | 61.6% | Benchgen evaluation | 2025-07 | | [HellaSwag](/benchmarks/hellaswag) | 78.6% | Benchgen evaluation | 2025-07 | | [HumanEval](/benchmarks/humaneval) | 75.0% | Benchgen evaluation | 2025-07 | | [MMLU-Pro](/benchmarks/mmlu-pro) | 50.6% | Benchgen evaluation | 2025-07 | ## Gemma 3n E4B vs Alternatives | Model | HumanEval | MMLU-Pro | Modality | Target | |---|---|---|---|---| | **Gemma 3n E4B** | 75.0% | 50.6% | Text+Vision+Audio | On-device | | [Gemma 3n E2B](/models/google/gemma-3n-e2b) | — | 40.5% | Text+Vision+Audio | On-device | | [Llama 3.2 3B Instruct](/models/meta/llama-3-2-3b-instruct) | — | — | Text | On-device | | [Gemma 3 12B](/models/google/gemma-3-12b) | 85.4% | 60.6% | Text+Vision | Server | Gemma 3n E4B vs Llama 3.2 3B: adds image and audio inputs at comparable parameter count. vs Gemma 3n E2B: higher accuracy (50.6% vs 40.5% MMLU-Pro) at higher compute cost. ## Related Models & Benchmarks - Compare: [Gemma 3n E2B](/models/google/gemma-3n-e2b) · [Gemma 3 12B](/models/google/gemma-3-12b) · [Llama 3.2 3B Instruct](/models/meta/llama-3-2-3b-instruct) - Benchmarks: [HumanEval](/benchmarks/humaneval) · [MMLU-Pro](/benchmarks/mmlu-pro) ## Frequently Asked Questions

What is Gemma 3n E4B?

Google's May 2025 on-device multimodal model with 4B effective parameters (MatFormer), scoring 75.0% HumanEval and 50.6% MMLU-Pro. Supports text, image, and audio inputs.

What does "E4B" mean in Gemma 3n?

E4B = 4 billion effective parameters. The MatFormer nested architecture uses dynamic compute allocation — "effective" refers to the active parameter count during inference.

--- *Specs from Google's official Gemma 3n release at Google I/O (May 2025) and Benchgen evaluations. Last updated 2026-07-24.*

Gemma 3n E4B Instructed — Files