IFM's K2-Horizon-36B-A4B Matches 20x-Larger Models on AA Index Using New MoVA Architecture

victormustar · x · 2026-09-22

IFM has open-sourced K2-Horizon-36B-A4B, which scores 25 on the Artificial Analysis Intelligence Index while activating only 4B parameters per token — matching models with over 20x its total parameters.

The gains come from MoVA (Mixture-of-Value Attention), a new architecture that applies MoE-style sparsity to the value vectors in multi-head attention, opening a second sparsity scaling axis beyond FFN-level MoE:

The model is available on Hugging Face as IFM/K2-Horizon-MoVA-36B-A4B.

Original post →

More from Models

Models channel →