跳转到主要内容

Gemma 3 1B Instruct

GoogleGemma开源权重Gemma · 商用许可

描述

The Gemma 3 1B model is a lightweight, 1-billion-parameter language model by Google, optimized for efficiency on resource-limited devices. At 529MB, it processes text at 2,585 tokens/second with a context window of 128,000 tokens. It supports 35+ languages but handles text-only input, unlike larger multimodal Gemma models. This balance of speed and efficiency makes it ideal for fast text processing on mobile and low-power devices.

发布日期
2025-03-13
参数规模
1.0B
上下文长度
—
支持模态
—

能力雷达图

30
general
20
coding
40
reasoning
17
science估算
34
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))

Chat

IFEvalGoogle Research (2023)80.2%自报

Factuality

SimpleQA2.2%自报

General

Global-MMLU-Lite34.2%自报

Language

WMT24++35.9%自报
MMLU-Pro14.7%自报
ECLeKTic1.4%自报

Math

GSM8k62.8%自报
MATH48.0%自报
HiddenMath15.8%自报

Reasoning

Natural2Code56.0%自报
HumanEvalOpenAI (2021)41.5%自报
BIG-Bench Hard39.1%自报
FACTS Grounding36.4%自报
MBPP0.35 / 100自报
GPQANYU + Cohere + Anthropic (2023)19.2%自报
BIG-Bench Extra Hard7.2%自报
Bird-SQL (dev)6.4%自报
LiveCodeBench1.9%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))
Chat
80
Instruction Following
80
Structured Output
80
Math
40
Grounding
40
Reasoning
30
General
30
Language
20
Physics
20
Factuality
20
Biology
20
Chemistry
20
Code
20
Legal
10
Finance
10
Healthcare
10

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