Skip to main content

Gemma 3n E4B Instruct

GoogleGemmaOpen WeightGemma · Commercial OK

Description

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.

Release Date
2025-06-26
Parameters
1.9B
Context Length
—
Modalities
image, text

Capability Radar

50
general
40
coding
40
reasoning
17
scienceest.
40
agents
80
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Code

Codegolf v2.216.8%SR

General

TriviaQA70.2%SR
MMLU64.9%SR
Global-MMLU-Lite64.5%SR
Global-MMLU60.3%SR
Include57.2%SR
OpenAI MMLU35.6%SR

Language

BoolQ81.6%SR
MMLU-Pro50.6%SR
WMT24++50.1%SR
MMLU-ProX19.9%SR
ECLeKTic1.9%SR

Math

MGSM60.7%SR
HiddenMath37.7%SR
AIME 202511.6%SR

Reasoning

ARC-E81.6%SR
PIQA81.0%SR
HellaSwagAI2 (2019)78.6%SR
HumanEvalOpenAI (2021)75.0%SR
Winogrande71.7%SR
MBPP0.64 / 100SR
ARC-C61.6%SR
DROP60.8%SR
BIG-Bench Hard52.9%SR
Social IQa50.0%SR
LiveCodeBench v525.7%SR
GPQANYU + Cohere + Anthropic (2023)23.7%SR
Natural Questions20.9%SR
LiveCodeBench13.2%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Language
50
Legal
50
Physics
50
Psychology
50
Reasoning
50
Finance
50
General
50
Healthcare
50
Creativity
50
Math
40
Code
40
Search
20
Biology
20
Chemistry
20

Pricing

No pricing data available

Speed

No speed data available

Provider Price Ranking

No provider data available

External Sources