谷歌开源Gemma 4：小模型也能思考推理
谷歌刚开源的Gemma 4系列模型，最反直觉的一点是：最小的模型只有23亿参数，却加入了“思考模式”——在回答前先生成推理链条，这让它在STEM、多模态等任务上性能飞跃，甚至能挑战参数大得多的前沿模型。
具体来说，Gemma 4提供了多种架构：从23亿到310亿参数的密集型和混合专家模型，所有尺寸都升级了视觉和音频编码器。特别的是，120亿参数的模型采用了一种统一的无编码器架构，能直接处理原始音频和图像块。而“思考模式”让模型在给出最终答案前，先输出一步步的推理过程，类似人类解题时的草稿。
谷歌还优化了推理速度、内存和长上下文能力。在多项基准测试中，Gemma 4的表现大幅超越前代，并在人类评分任务中与更大的开源模型不相上下。
这不是你明天就能直接用的工具，但它释放了一个强烈信号：小模型+推理链，可能是让AI更高效、更透明的关键路径。对于关注AI前沿的读者，这意味着开源模型的能力天花板正在被重新定义。
📄 原文摘要(英文)
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemma 4 model suite features dense and Mixture-of-Experts architectures, ranging from 2.3B to 31B parameters. Alongside improved vision and audio encoders for all model sizes, we propose a unified, encoder-free architecture for our 12B model, which ingests raw audio and image patches. Furthermore, we integrate a thinking mode, enabling Gemma models to generate reasoning traces prior to responding. We improve inference speed, memory, and compute efficiency, as well as long-context abilities through critical design choices. Gemma 4 establishes a leap in performance across STEM, multimodal, and long-context benchmarks, and rivals larger, frontier open models in human-rated tasks.