Gemma 3
Google released the 多模态 model · Launched on 2025-03
Open Source
多模态
开源
API 可用
模型简介
Gemma 3 is an open-source lightweight model series released by Google, built on Gemini 2.0 technology. It offers four sizes from 1B to 27B, supports text and vision multimodal input, and has a 128K token context window. Gemma 3 leads in performance among models of the same parameter size, can run on a single GPU or even a phone, and is a high-quality choice for fine-tuning and deployment in the open-source community.
核心特性
- 多规格可选
- 128K 上下文
- 文本+视觉多模态
- 可本地运行
核心优势
- 同规模性能最优
- 部署灵活
- 开源可商用
技术规格
参数量
1B / 4B / 12B / 27B
上下文窗口
128K tokens
API 支持
Yes
开源状态
Open Source
发布日期
2025-03
提供商
Google
价格信息
免费开源
基准测试
27B 版本在 MMLU 上达 75.0%，超越同规模开源模型