hugpadhugpad

IFM / K2-Horizon-MoVA-36B-A4B-FP8

Text Generation37B88016Updated Oct 15, 2026
Hugging Face

Downloads

880

Likes

16

Last updated

Oct 15, 2026

License

apache-2.0

[!NOTE] This repository contains an FP8-quantized version of IFM/K2-Horizon-MoVA-36B-A4B. Only the routed-expert linear layers in transformer layers 3–47 are quantized to FP8: - Weights: static FP8 E4M3FN, one FP32 scale per 128128 block. - Activations: dynamic FP8, one scale…

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • k2_horizon
  • text-generation
  • k2-horizon
  • 36b
  • mova

Technical specifications

Parameters37B
Librarytransformers
Languagesen
Base modelIFM/K2-Horizon-MoVA-36B-A4B
Licenseapache-2.0