header-langage
简体中文
繁體中文
English
Tiếng Việt
한국어
日本語
ภาษาไทย
Türkçe
Scan to Download the APP
Partnered With:

ByteDance discusses a training parameter model exceeding 5 trillion, potentially becoming the largest known model in the country in terms of parameters.

BlockBeats News, August 6, ByteDance is discussing training a model with over 5 trillion parameters, surpassing Alibaba's Qwen3.8-Max (2.4 trillion parameters) and Dark Matter's K3 (2.8 trillion parameters), making it the largest known model in China in terms of parameters. Generally, a larger model size corresponds to a higher level of intelligence.


However, this plan is still in the early stages and does not guarantee the eventual release of the model. The new model will be led by Xiang Liang, head of Seed Foundation, in collaboration with Shen Ke, head of Large Language Model Pre-training Data. To facilitate this, Seed is reorganizing, clarifying responsibilities, and allocating resources. (To be continued)

Correction/Report
Submit
Add Library
Visible to myself only
Public
Save
Choose Library
Add Library
Cancel
Finish