AI Radar
Support
LiveUpdated 2026-09-21 18:40 UTC

K2-Horizon-36B-A4B scores 25 on the Artificial Analysis Intelligence Index, matching…

K2-Horizon-36B-A4B scores 25 on the Artificial Analysis Intelligence Index, matching models with over 20× the total…K2-Horizon-36B-A4B scores 25 on the Artificial Analysis Intelligence Index, matching models with over 20× the total…

This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.

K2-Horizon-36B-A4B scores 25 on the Artificial Analysis Intelligence Index, matching models with over 20× the total parameters while using 4B active parameters per token. These capabilities come from our new architecture MoVA (Mixture-of-Value Attention), which incorporates MoE-based sparsity into the compute of value vectors in multi-head attention. It opens a second axis for scaling sparsity in an LLM, beyond MoE in the FFN module. Importantly, MoVA enjoys the following advantages: • Simple and compatible with efficient attention algorithms, such as flash attention, GQA, and sparse attent

Posted by Institute of Foundation Models (3.5k followers) 1 h ago · 150 likes · 8.3k views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: k2-horizon-mova-36b-a4b.

More AI work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 39.7k posts from 5k X accounts over the last 14 days, 1.6k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 18:40 UTC. Full method.