hugpadhugpad

Mia-AiLab / MiniMax-M3.1-Flash-EXL3-EAQ-v1-3.5-bpw

Text Generation97B1K3Updated Oct 23, 2026
Hugging Face

Downloads

1K

Likes

3

Last updated

Oct 23, 2026

License

Not available

EAQ v1 (EXL3 format) quantization of MiniMaxAI/MiniMax-M3.1-Flash, 60 layers, 128 routed experts with top-4 routing, 3.55 bits per weight on average (target 3.5) and a 6-bit LM head. The weights are 179.4 GiB (192.6 GB) in 25 shards.

Tasks & library

  • text generation
  • exllamav3

Tags

  • exllamav3
  • minimax_m3_vl
  • exl3
  • eaq
  • quantized
  • moe

Technical specifications

Parameters97B
Libraryexllamav3
LanguagesNot available
Base modelMiniMaxAI/MiniMax-M3.1-Flash
LicenseNot available