Institute of Foundation Models (MBZUAI) · Fully Open MoE

K2-Horizon-375B-A23B

The flagship of IFM's K2 Horizon family: a sparse mixture-of-experts model with 375B total and 23B active parameters and a native 512K context. Trained on about 15T pretraining tokens, four context-extension stages, then reinforcement learning across five merged expert models. Weights, training data, code and intermediate checkpoints from every stage are public under Apache 2.0, and the model card's artifact table marked them all available as of 28 September after the family's 3 September launch with six sizes from 0.9B to 375B. IFM reports 70.2% on Terminal-Bench 2.1, 65.3% on Toolathlon Verified and 87.3% on GPQA Diamond, all vendor-reported against older comparison models. Serving recipes cover vLLM and SGLang on 8 GPUs; the technical report was still marked in progress.