跳轉到主要內容

Gemma 3 1B Instruct

GoogleGemma開源權重Gemma · 商用許可

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.

發布日期
2025-03-13
參數規模
1.0B
上下文長度
—
支援模態
—

能力雷達圖

30
general
20
coding
40
reasoning
17
science估算
34
agents
0
multimodal

缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。

排行榜排名

暫無排名資料

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)80.2%自報

Factuality

SimpleQA2.2%自報

General

Global-MMLU-Lite34.2%自報

Language

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

Math

GSM8k62.8%自報
MATH48.0%自報
HiddenMath15.8%自報

Reasoning

Natural2Code56.0%自報
HumanEvalOpenAI (2021)41.5%自報
BIG-Bench Hard39.1%自報
FACTS Grounding36.4%自報
MBPP0.35 / 100自報
GPQANYU + Cohere + Anthropic (2023)19.2%自報
BIG-Bench Extra Hard7.2%自報
Bird-SQL (dev)6.4%自報
LiveCodeBench1.9%自報

AA 評測指數

(Artificial Analysis)

暫無 AA 評測資料

LLM Stats 分類評分

(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

定價

輸入價格免費
輸出價格免費

速度

暫無速度資料

供應商價格排行

暫無提供商資料

外部連結