跳转到主要内容

Gemma 3n E2B Instruct

GoogleGemma开源权重Gemma · 商用许可

描述

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.

发布日期
2025-06-26
参数规模
1.9B
上下文长度
—
支持模态
—

能力雷达图

40
general
30
coding
40
reasoning
17
science估算
37
agents
0
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

暂无排名数据

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Code

Codegolf v2.211.0%自报

General

TriviaQA60.8%自报
MMLU60.1%自报
Global-MMLU-Lite59.0%自报
Global-MMLU55.1%自报
Include38.6%自报
OpenAI MMLU22.3%自报

Language

BoolQ76.4%自报
WMT24++42.7%自报
MMLU-Pro40.5%自报
MMLU-ProX8.1%自报
ECLeKTic2.5%自报

Math

MGSM53.1%自报
HiddenMath27.7%自报
AIME 20256.7%自报

Reasoning

PIQA78.9%自报
ARC-E75.8%自报
HellaSwagAI2 (2019)72.2%自报
Winogrande66.8%自报
HumanEvalOpenAI (2021)66.5%自报
MBPP0.57 / 100自报
DROP53.9%自报
ARC-C51.7%自报
Social IQa48.8%自报
BIG-Bench Hard44.3%自报
GPQANYU + Cohere + Anthropic (2023)24.8%自报
LiveCodeBench v518.6%自报
Natural Questions15.5%自报
LiveCodeBench13.2%自报

AA 评测指数

(Artificial Analysis)

暂无 AA 评测数据

LLM Stats 分类评分

(LLM Stats (zeroeval))
Language
50
Physics
50
Psychology
50
Reasoning
50
Creativity
50
Legal
40
Math
40
Finance
40
General
40
Healthcare
40
Code
30
Search
20
Biology
20
Chemistry
20

定价

输入价格免费
输出价格免费

速度

暂无速度数据

供应商价格排行

暂无提供商数据

外部链接