# 字节跳动预训练10万亿参数模型

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-07 17:10
- AIHOT 分数：61
- AIHOT 链接：https://aihot.virxact.com/items/cmsiq7hmw1oocronkffzzohd2
- 原文链接：https://x.com/rohanpaul_ai/status/2085654823043789277

## AI 摘要

FT：字节跳动据报正在预训练一个参数高达10万亿的AI模型，远超Kimi K3的2.8万亿参数规模。

FT还报道称，字节跳动一年多来一直避免蒸馏竞争对手的模型，倾向于独立开发模型。

如果上述训练成功，字节跳动将证明其能够在不依赖竞争对手模型作为教师的情况下，执行前沿规模的预训练。

## 正文

FT: ByteDance is reportedly pre-training an AI model with up to 10T parameters, far exceeding Kimi K3's 2.8Trn param size.

FT also reported that ByteDance has avoided distilling rival models for more than a year, preferring independent model development.

If the reported run succeeds, ByteDance will have shown it can execute frontier-scale pretraining without leaning on a rival model as teacher.