跳到正文
HNHacker News·
暂不在当前实时榜单

Timestral: Mistral's time-series foundation models

AI 摘要

Mistral's Timestral models are time-series foundation models designed for efficient inference without a GPU. On a standard server CPU with 8 threads, the 5M model forecasts one day ahead from three weeks of 15-minute history in 10 ms, while the 209M model takes 140 ms. Smaller models like the 28M are five times faster than the 209M model, and the 123M model achieves a score within 0.2% of the 209M model at three quarters of its latency. Timestral is released under the Modified MIT license.

时间与来源

时间显示为 UTC

显示时区:UTC

本地时区尚不可用,暂时显示 UTC。

收录当时偏移:UTC+02026年10月19日 12:00 UTC

收录
2026年10月19日 12:00
来源类型
官方发布
爆款判定
判定依据
热度约为该来源近期上榜条目中位水平的 6.9 倍
指标对比
485 vs 中位 70(20 条基线样本)
检出时间
10/19 13:00

本站未收录正文。

前往源站阅读 →
来源·Hacker News·mistral.ai