hugpadhugpad

deepseek-ai / DeepSeek-V4-Pro

Text Generation1599B367.5K5.7KUpdated Jun 22, 2026
Hugging Face

Downloads

367.5K

Likes

5.7K

Last updated

Jun 22, 2026

License

mit

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million…

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • deepseek_v4
  • text-generation
  • 8-bit
  • fp8

Technical specifications

Parameters1599B
Librarytransformers
LanguagesNot available
Licensemit