Gemma 4 推出多模态开源大模型，提升推理与效率。
Gemma 4 Technical Report
- 采用密集与专家混合架构，参数量2.3B至31B，支持多模态输入。
- 12B模型无需编码器，直接处理原始音视频块，推理速度更快。
- 新增思考模式生成推理过程，长文本与跨领域任务表现领先。
我们推出新一代开源多模态语言模型 Gemma 4，属于 Gemma 模型家族。该系列模型在计算效率和推理能力方面实现显著提升，包含从 2.3B 到 31B 参数的密集型与混合专家（Mixture-of-Experts）架构。所有模型均配备优化后的视觉与音频编码器。针对 12B 模型，提出一种无编码器统一架构，可直接接收原始音频与图像块输入。此外，引入“思考模式”，使模型可在回复前生成推理轨迹。通过关键设计优化，显著提升推理速度、内存占用与计算效率，并增强长上下文处理能力。Gemma 4 在 STEM、多模态及长文本基准测试中表现跃升，人类评估任务中媲美更大规模的前沿开源模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。