Llama 3.1 405B
AI模型
语言
上一代
The first open-weights model at closed-frontier scale.
您正在查看一条 AI 模型记录：谁构建了它、它能做什么，以及其背后的硬件与数据。
Llama 3.1's 405B dense model (July 2024) was trained on 15.6 trillion tokens across ~16,000 H100s (~3.8×10²⁵ FLOP, disclosed) and matched GPT-4-class results — the moment open weights reached the frontier's neighborhood. Its disclosed training details made it the reference public datapoint for frontier training economics.
规格与关键参数
每个数据均标注来源依据：厂商规格、厂商声明、公开报道、估算或官方数据。"未公开披露"即字面含义——我们从不捏造数值。
Overview
Training compute
~3.8×10²⁵ FLOP (from disclosed GPU-hours)Published paper
Training hardware
~16,000 × H100 (two 24k clusters built)Published paper
它如何与整个技术栈相连
本记录的关联链接一览——点击分组可直接跳转。
开发方
训练于
基础来源
后继产品
前代产品
竞品
来源
记录审阅截至 2026-01-15 — 查看 方法论.