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 v2.2
11.0%自报
General
TriviaQA
60.8%自报
MMLU
60.1%自报
Global-MMLU-Lite
59.0%自报
Global-MMLU
55.1%自报
Include
38.6%自报
OpenAI MMLU
22.3%自报
Language
BoolQ
76.4%自报
WMT24++
42.7%自报
MMLU-Pro
40.5%自报
MMLU-ProX
8.1%自报
ECLeKTic
2.5%自报
Math
MGSM
53.1%自报
HiddenMath
27.7%自报
AIME 2025
6.7%自报
Reasoning
PIQA
78.9%自报
ARC-E
75.8%自报
HellaSwagAI2 (2019)
72.2%自报
Winogrande
66.8%自报
HumanEvalOpenAI (2021)
66.5%自报
MBPP
0.57 / 100自报
DROP
53.9%自报
ARC-C
51.7%自报
Social IQa
48.8%自报
BIG-Bench Hard
44.3%自报
GPQANYU + Cohere + Anthropic (2023)
24.8%自报
LiveCodeBench v5
18.6%自报
Natural Questions
15.5%自报
LiveCodeBench
13.2%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))Language50
Physics50
Psychology50
Reasoning50
Creativity50
Legal40
Math40
Finance40
General40
Healthcare40
Code30
Search20
Biology20
Chemistry20
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