Minions：端侧小模型与云端大模型协作降低 LLM 成本

AI 摘要

Together AI 的研究团队提出了一种名为 Minions 的方法，通过让小型端侧模型与云端前沿模型协作，将大量 LLM 工作负载转移到消费设备上，仅本地读取长上下文，从而降低云成本且几乎不损失质量。实验表明，Minions 在保持 97.9% 准确率的同时，成本仅为云端方案的 17.5%。该方法通过分解-执行-聚合循环，解决了小模型长上下文和多步指令的弱点，并展示了模型选择、推理计算扩展和顺序通信对成本-准确率权衡的影响。

正文节选

Summary We present Minions, a method that shifts a substantial portion of LLM workloads to consumer devices by having small on-device models collaborate with frontier models in the cloud. By only reading long contexts locally, we reduce cloud costs with minimal or no quality degradation. We imagine a future where an “intelligence layer” running persistently on-device interacts with frontier models in the cloud to deliver applications with cost-effective, “always-on” intelligence. The Tailwinds:

发布时间：—

抓取时间：2026-08-04 02:56

来源机构：Together AI