IFM's K2-Horizon-7B outscores Qwen3.6-27B despite being a 7B model

rupspace · x · 2026-09-17

IFM released K2-Horizon-7B, claiming a score of 21 on the Artificial Analysis Intelligence Index — reportedly 50% above the next best model under 10B, beating Qwen3.6-35B-A3B and closely matching Qwen3.6-27B. The team says the model "exceeded expectations since pre-training." Weights and an 8-bit quantization are on Hugging Face, plus "Uno," a diffusion-augmented speed-up variant.

Related event: IFM's open-source 7B model K2-Horizon nearly matches 27B-level performance(2 posts)→

Original post →

More from Models

Models channel →