hugpadhugpad

Inferact / MiniMax-M3-EAGLE3-GQA

Text Generation3.1B5.1K3Updated Jul 15, 2026
Hugging Face

Downloads

5.1K

Likes

3

Last updated

Jul 15, 2026

License

mit

Inferact/MiniMax-M3-EAGLE3-GQA is a grouped-query-attention (GQA) EAGLE3 draft model for accelerating inference of MiniMax-M3, served with vLLM and trained with TorchSpec.

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • llama
  • eagle3
  • speculative-decoding
  • draft-model
  • gqa

Technical specifications

Parameters3.1B
Librarytransformers
LanguagesNot available
Base modelMiniMaxAI/Minimax-M3-preview
Licensemit