hugpadhugpad

abenzerps / K2-Horizon-MoVA-36B-A4B-MLX-4bit

Text Generation37B6624Updated Oct 11, 2026
Hugging Face

Downloads

662

Likes

4

Last updated

Oct 11, 2026

License

apache-2.0

MLX 4-bit conversion of IFM/K2-Horizon-MoVA-36B-A4B, a sparse Mixture-of-Experts model with Mixture-of-Values attention (MoVA), 36B total parameters, and approximately 4B active parameters per token. The source checkpoint supports a native context length of 524,288 tokens (512K).

Tasks & library

  • text generation
  • mlx

Tags

  • mlx
  • k2_horizon
  • mlx-lm
  • 4-bit
  • k2-horizon
  • long-context

Technical specifications

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