Gemma 3n E4B 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
image, text
能力雷达图
50
general
40
coding
40
reasoning
17
science估算
40
agents
80
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
16.8%自报
General
TriviaQA
70.2%自报
MMLU
64.9%自报
Global-MMLU-Lite
64.5%自报
Global-MMLU
60.3%自报
Include
57.2%自报
OpenAI MMLU
35.6%自报
Language
BoolQ
81.6%自报
MMLU-Pro
50.6%自报
WMT24++
50.1%自报
MMLU-ProX
19.9%自报
ECLeKTic
1.9%自报
Math
MGSM
60.7%自报
HiddenMath
37.7%自报
AIME 2025
11.6%自报
Reasoning
ARC-E
81.6%自报
PIQA
81.0%自报
HellaSwagAI2 (2019)
78.6%自报
HumanEvalOpenAI (2021)
75.0%自报
Winogrande
71.7%自报
MBPP
0.64 / 100自报
ARC-C
61.6%自报
DROP
60.8%自报
BIG-Bench Hard
52.9%自报
Social IQa
50.0%自报
LiveCodeBench v5
25.7%自报
GPQANYU + Cohere + Anthropic (2023)
23.7%自报
Natural Questions
20.9%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
Legal50
Physics50
Psychology50
Reasoning50
Finance50
General50
Healthcare50
Creativity50
Math40
Code40
Search20
Biology20
Chemistry20
定价
暂无定价数据
速度
暂无速度数据
供应商价格排行
暂无提供商数据