Google DeepMind 发布 Gemma 4 QAT 系列模型，采用量化感知训练，在压缩内存需求的同时比常规训练后量化保留更多质量。该系列支持 Q4_0 格式和一种新的移动端专用量化格式，Gemma 4 E2B 约 1GB 内存即可运行，纯文本版本所需内存甚至低于 1GB，让手机、笔记本、边缘设备和消费级 GPU 上的本地 AI 更实用。
Google DeepMind released new Gemma 4 QAT models that make the model family much more efficient for local, on-device use.
Using Quantization-Aware Training, the models are trained with compression in mind, which reduces memory needs while preserving more quality than standard post-training quantization. The release includes support for the popular Q4_0 format and a new mobile-specialized quantization format.
Gemma 4 E2B can now run with around 1GB of memory (!), and the text-only version can even require less than 1GB (!). That makes local AI on phones, laptops, edge devices, and consumer GPUs far more practical.
Really cool to see.
来源：@kimmonismus · x.com