本地AI模型已经能够像前沿云端模型一样,回答89%的日常聊天与推理查询,这一结论在超过一百万条真实查询及20多个本地模型的广泛测试中均得到验证。¹
这意味着我们正在用每瓦特电力产生更多智能:用同样数量的电子完成更多工作。¹
追踪计算效率随时间的变化并非新鲜事。库梅定律(Koomey's law)发现,数十年来每瓦特计算能力大约每1.5年翻一番,这一趋势将大型主机的算力浓缩进了笔记本电脑的机身之中。²³
正如每瓦特性能推动了从大型主机到个人电脑的转型,每瓦特智能也将引领AI向边缘端迁移。
—— Jon Saad-Falcon、Avanika Narayan 等人,《每瓦特智能》
如今GPU的效率提升曲线则更为平缓,过去15年间大约每2.7年翻一番,而非每1.5年。⁴
其影响同样令人瞩目:最佳本地模型对阵前沿模型的胜率/平局率,从2023年的23.2%攀升至2025年的71.3%,每年约提升20个百分点。到2026年,由另一个本地AI为任务选出的本地模型,这一数字将跃升至近90%。⁵
效率也沿着趋势线同步提升:同期每瓦特智能提升了5.3倍,其中3.1倍来自更优秀的模型,1.7倍来自更先进的芯片。计算机更快了,模型更聪明了,最终受益的是终端用户。
⁵
云端对于长链条多步推理、最艰深的技术领域,以及依赖规模与并行化的任务仍然不可或缺。在许多应用场景中,云端硬件对本地硬件仍保有优势。云端推理相比本地模型可带来40%的能效提升。⁶ 数据中心采用批量处理查询的方式,而这一技巧是每次仅服务一个用户的本地硬件目前还无法使用的。
但对于大部分日常知识工作而言,完全没有必要将查询发送到数据中心。本地模型加路由器的组合,足以应对绝大多数工作任务。⁷
与全云端基线相比,这种方式还能削减80%的能耗、77%的计算量以及74%的成本。
大型主机走进了个人生活。你的数据中心也将如此。
-
Jon Saad-Falcon、Avanika Narayan 等人所著《每瓦智能:衡量本地 AI 的智能效率》,斯坦福大学与 Together AI,2025 年 11 月。arXiv:2511.07885。另见斯坦福 Hazy Research 综述。 ↩︎ ↩︎
-
库米定律,维基百科。 ↩︎
-
瓦特衡量的是功率,即能量消耗的速率,而焦耳衡量的是能量本身;库米最初的指标是每焦耳的计算量,但底层趋势与现在 AI 模型所追踪的每瓦智能是同一个。 ↩︎
-
Anson Ho、Ege Erdil 与 Tamay Besiroglu,《CMOS 微处理器能效的极限》,2023 年。arXiv:2312.08595。 ↩︎
-
71.3% 和 89% 是同一份 2025 年数据中的两个不同测量值,而非同一数字在不同时间点的数值。71.3% 是表现最佳的单款本地模型对阵前沿模型的胜率/平局率,也是此图表所绘制的趋势线(2023 年为 23.2%,2024 年为 48.7%,2025 年为 71.3%)。89% 则是另一个更高的上限:将每个查询路由到所测试的 20 多款本地模型中处理该查询效果最佳的那一款,其表现比任何单一模型高出 16.3 到 28.8 个百分点。这一增益是选择效应所致:论文指出,本地路由从 20 多款多样化模型中挑选,而前沿云端模型只有三款,因此在某些基准测试上,本地模型集成的最佳表现甚至超越了云端模型集成的最佳表现。可供选择的候选模型更多——而不仅仅是路由更智能——才是提升准确率的原因。这两个数字均来自同一项研究,且两者互不取代。 ↩︎ ↩︎
-
Jon Saad-Falcon、Avanika Narayan 等人所著《每瓦智能:衡量本地 AI 的智能效率》,斯坦福大学与 Together AI,2025 年 11 月。运行相同模型时,云端加速器每瓦智能至少比本地芯片高出 1.4 倍,即约 40% 的效率优势。arXiv:2511.07885。 ↩︎
-
大多数 AI 工作可以等待,tomtunguz.com。 ↩︎
Local AI models can already answer 89% of everyday chat & reasoning queries as well as a frontier cloud model, a result that holds broadly across more than a million real queries & 20+ local models tested.1
That means we’re generating more intelligence per watt of electricity : more work from the same number of electrons.1
Tracking computing efficiency over time is not new. Koomey’s law found that computing power per watt doubled roughly every 1.5 years for decades, a trend that shrank the power of a mainframe into a laptop’s chassis.23
Just as performance-per-watt guided the mainframe-to-PC transition, intelligence-per-watt will guide AI’s transition to the edge.
— Jon Saad-Falcon, Avanika Narayan, et al., “Intelligence per Watt”
GPUs follow a more languid curve today, doubling efficiency roughly every 2.7 years over the last 15 years, not every 1.5 years.4
The impact is no less impressive : the best local model’s win/tie rate against a frontier model, rose from 23.2% in 2023 to 71.3% in 2025, adding roughly 20 percentage points a year. In 2026, a local model selected for the task by another local AI bumps that number to nearly 90%.5
Efficiency improved alongside the trend line : intelligence-per-watt rose 5.3x over the same period, split into a 3.1x gain from better models & a 1.7x gain from better chips. Computers are faster, models are smarter. And the end user benefits.
5
Cloud remains essential for long multi-step reasoning, the hardest technical domains, & workloads where scale & parallelization matter. Cloud hardware still holds an edge over local hardware in many use cases. Cloud inference delivers a 40% energy efficiency gain relative to local models.6 Datacenters batch queries, a trick local hardware serving one user at a time cannot use, yet.
But for much of everyday knowledge work, there is no reason to send the query to the data center at all. The combination of local models plus a router is sufficient for the supermajority of work.7
It also cuts energy 80%, compute 77%, & cost 74% against an all-cloud baseline.
Mainframes became personal. So will your data center.
-
Jon Saad-Falcon, Avanika Narayan, et al., “Intelligence per Watt: Measuring Intelligence Efficiency of Local AI,” Stanford University & Together AI, November 2025. arXiv:2511.07885. See also the Stanford Hazy Research overview. ↩︎ ↩︎
-
Koomey’s law, Wikipedia. ↩︎
-
Watts measure power, the rate energy is drawn, & joules measure the energy itself; Koomey’s original metric was computations per joule, but the underlying trend is the same one intelligence per watt now tracks for AI models. ↩︎
-
Anson Ho, Ege Erdil & Tamay Besiroglu, “Limits to the Energy Efficiency of CMOS Microprocessors,” 2023. arXiv:2312.08595. ↩︎
-
71.3% & 89% are two different measurements from the same 2025 data, not the same number at different times. 71.3% is the best single local model’s win/tie rate against a frontier model, the trend line this chart plots (23.2% in 2023, 48.7% in 2024, 71.3% in 2025). 89% is a separate, higher ceiling: routing each query to whichever of the 20+ local models tested handles it best beats any single model by 16.3 to 28.8 percentage points. That gain is a selection effect: the paper notes local routing draws from 20+ diverse models versus three frontier cloud models, so on some benchmarks the best-of-local ensemble even surpasses best-of-cloud. More candidates to choose from, not just smarter routing, is what raises accuracy. Both figures come from the same study & neither supersedes the other. ↩︎ ↩︎
-
Jon Saad-Falcon, Avanika Narayan, et al., “Intelligence per Watt: Measuring Intelligence Efficiency of Local AI,” Stanford University & Together AI, November 2025. Cloud accelerators deliver at least 1.4x higher intelligence-per-watt than local chips running the same models, roughly a 40% efficiency premium. arXiv:2511.07885. ↩︎
-
Most AI Work Can Wait, tomtunguz.com. ↩︎