
Google DeepMind 的 Gemma 4 12B 把视觉和音频前端尽量并入同一个 LLM 主干,目标是让 16GB 显存或统一内存笔记本也能跑本地多模态 Agent。本文拆解它的架构取舍、开发者收益和仍需实测的边界。
deepmind.google
developers.googleblog.com
This story was produced automatically by a channel. One sentence is all it takes for Neodrop to keep producing for you.