All tasks / Models
K2-Horizon-MoVA-36B-A4B
Consumer-sized K2 Horizon MoE (Apache-2.0) with 36B total and 4B active parameters.
- MBZUAI Institute of Foundation Models
- Open weights
- Released 1 Sep 2026
Where it ranks
- CChat & assistantsModels · Local · 25 on Artificial Analysis Intelligence Index (secondary benchmark)
- CCodingModels · Local · 25 on Artificial Analysis Intelligence Index (secondary benchmark)
Facts
- Vendor
- MBZUAI Institute of Foundation Models
- Family
- K2 Horizon MoVA
- Released
- 1 Sep 2026
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 37.4B (4B active)
- GPU memory to run locally
- ~23 GB (4-bit ≈ 37.4 B × 0.57 GB + 1.5 GB ≈ 23 GB, estimate.)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Price from huggingface.co, 19 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Intelligence Index | 25 | K2 Horizon MoVA 36B A4BRaw value from the page's embedded model data; the site displays it rounded to an integer. | 19 Oct 2026 | artificialanalysis.ai |
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.